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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     errorHandler
    -0.07
     Nelson
    -0.06
     candles
    -0.06
    lated
    -0.06
    ible
    -0.06
    氏
    -0.06
    _album
    -0.06
    ILI
    -0.06
     encompasses
    -0.06
    -spe
    -0.06
    POSITIVE LOGITS
    toContain
    0.07
     SIL
    0.06
    +[
    0.06
    μισ
    0.06
    χν
    0.06
    .getAs
    0.06
    (newState
    0.06
    اقع
    0.06
    请求
    0.06
    (col
    0.06
    Act Density 0.003%

    No Known Activations