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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Players
    -0.07
    範
    -0.06
    ICK
    -0.06
    _CONFIRM
    -0.06
    弱
    -0.06
     Thermal
    -0.06
    ولة
    -0.06
     분류
    -0.06
    ंज
    -0.06
     executives
    -0.06
    POSITIVE LOGITS
     DIV
    0.07
    datable
    0.06
    (月
    0.06
     플
    0.06
     เกม
    0.06
     드라마
    0.06
    .getDate
    0.06
    ้วย
    0.06
    ันย
    0.06
    !..
    0.06
    Act Density 0.012%

    No Known Activations