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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    APPER
    -0.07
    /signup
    -0.07
    ifty
    -0.06
    icas
    -0.06
    �
    -0.06
     downhill
    -0.06
     Thorn
    -0.06
    /cache
    -0.06
    SetColor
    -0.06
    ۴۰
    -0.06
    POSITIVE LOGITS
    .NaN
    0.07
     tá
    0.07
    jon
    0.07
     Thank
    0.06
    聖
    0.06
    ,column
    0.06
    erture
    0.06
     Veter
    0.06
     Country
    0.06
    .mul
    0.06
    Act Density 0.047%

    No Known Activations