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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron responds to tokens in photo-caption or image-credit metadata (e.g. the parentheses and “Photo…/Getty Images” lines).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ForgeryToken
    -0.07
     HttpStatusCode
    -0.07
     Bbw
    -0.07
     lowercase
    -0.06
    (lhs
    -0.06
     NV
    -0.06
     CrossRef
    -0.06
    _tokenize
    -0.06
    _Osc
    -0.06
     frail
    -0.06
    POSITIVE LOGITS
     TIMES
    0.07
    Big
    0.07
     Este
    0.07
    .Card
    0.06
    unction
    0.06
     electrons
    0.06
    Green
    0.06
    =add
    0.06
     انتخاب
    0.06
    queda
    0.06
    Act Density 0.008%

    No Known Activations