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

    Neuronpedia

    INDEX
    Explanations

    Numbers and identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IR
    -0.07
     ROM
    -0.06
    每一位
    -0.06
     Monday
    -0.06
    TURN
    -0.06
    らない
    -0.06
    ymous
    -0.06
     immediate
    -0.06
     Tuesday
    -0.06
    קיץ
    -0.06
    POSITIVE LOGITS
    <Result
    0.08
    仡
    0.07
    ⋰
    0.07
    (util
    0.07
     Wr
    0.07
    _operations
    0.07
    נפתח
    0.07
    }-{
    0.07
    essler
    0.07
    ,bool
    0.07
    Act Density 0.326%

    No Known Activations