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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     уж
    -0.08
    müştür
    -0.06
    Threads
    -0.06
    tip
    -0.06
     baseman
    -0.06
     zombie
    -0.06
     Greece
    -0.06
    カード
    -0.06
     cameras
    -0.06
    cors
    -0.06
    POSITIVE LOGITS
     این
    0.06
    ................
    0.06
    (fb
    0.06
    (BigDecimal
    0.06
     Enlight
    0.06
    /she
    0.06
    ,**
    0.06
    ="{{$
    0.06
     національ
    0.06
    LObject
    0.06
    Act Density 0.035%

    No Known Activations