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

    Neuronpedia

    INDEX
    Explanations

    respect and morality

    np_max-act · gemini-2.0-flash

    The neuron activates on verbs in their “-ing” (gerund/participle) form.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     �
    -0.07
    _entity
    -0.06
    اصر
    -0.06
     Beirut
    -0.06
    Contin
    -0.06
     VARIANT
    -0.06
    ्गत
    -0.06
     برنامج
    -0.06
    iera
    -0.06
    _enum
    -0.06
    POSITIVE LOGITS
    	JSONObject
    0.07
    stand
    0.06
     criticized
    0.06
    Blue
    0.06
    �프
    0.06
     ft
    0.06
    enter
    0.06
     anthem
    0.06
    alc
    0.06
    .Session
    0.06
    Act Density 0.001%

    No Known Activations