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

    Neuronpedia

    INDEX
    Explanations

    version, unit

    np_max-act · gemini-2.0-flash

    The neuron is triggered by passive‐voice verb constructions (forms of “to be” combined with a past participle).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    کنان
    -0.06
    assing
    -0.06
    Supply
    -0.06
    .Reset
    -0.06
    BN
    -0.06
    ータ
    -0.06
    woods
    -0.06
    Apple
    -0.05
    Music
    -0.05
    -btn
    -0.05
    POSITIVE LOGITS
     gravy
    0.07
    (gc
    0.07
     dek
    0.07
     policies
    0.07
     рос
    0.06
     hires
    0.06
     Мож
    0.06
    ////////////////////////////////////////////////////////////////////////////////////////////////
    0.06
    .�
    0.06
    �
    0.06
    Act Density 0.047%

    No Known Activations