Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    details about the Python programming language, including its features, uses, and functionalities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    Neuron 1: this neuron fires on present-participle or gerund forms ending in “-ing.” Neuron 2: this neuron fires on terms naming acute medical conditions or emergencies. Neuron 3: this neuron fires on expressions of collective unity or togetherness (e.g. “we’re all in this together”). Neuron 4: this neuron fires on descriptive feature words or attribute terms used when listing or explaining characteristics.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    تاب
    -0.07
     Apollo
    -0.06
     gọi
    -0.06
     Meaning
    -0.06
     ':
    -0.06
    _PROPERTY
    -0.06
     denen
    -0.06
     congratulations
    -0.06
    捕
    -0.06
     Kun
    -0.06
    POSITIVE LOGITS
    among
    0.07
     テ
    0.07
    ANC
    0.07
    Illuminate
    0.06
     lez
    0.06
    .\
    0.06
    techn
    0.06
     pozit
    0.06
    .springframework
    0.06
    preh
    0.06
    Act Density 0.112%

    No Known Activations