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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    individual
    -0.07
    (author
    -0.06
    .setCancelable
    -0.06
    .Allow
    -0.06
     handy
    -0.06
    _matrix
    -0.06
     Eleven
    -0.06
    라피
    -0.05
    customer
    -0.05
    ']
    -0.05
    POSITIVE LOGITS
     Beard
    0.08
     locals
    0.06
    Rev
    0.06
    _DMA
    0.06
    �
    0.06
    アメリカ
    0.06
     kênh
    0.06
     jours
    0.06
    ilin
    0.06
    ynı
    0.06
    Act Density 0.122%

    No Known Activations