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

    Neuronpedia

    INDEX
    Explanations

    ATE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pickle
    -0.07
     prepar
    -0.06
    _minus
    -0.06
     Coins
    -0.06
     cổ
    -0.06
    @click
    -0.06
    ιλο
    -0.06
     winger
    -0.06
     ชนะ
    -0.06
     Slovakia
    -0.06
    POSITIVE LOGITS
     truncate
    0.08
    情况
    0.07
     quant
    0.07
    seau
    0.07
    uncate
    0.06
    recur
    0.06
    ươi
    0.06
    curity
    0.06
     NSRange
    0.06
    truncate
    0.06
    Act Density 0.001%

    No Known Activations