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

    Neuronpedia

    INDEX
    Explanations

    nothing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Costume
    -0.07
    (outfile
    -0.07
    DEFINE
    -0.06
    šel
    -0.06
    cete
    -0.06
    sınız
    -0.06
    larını
    -0.06
     typing
    -0.06
     nichž
    -0.06
    getFile
    -0.06
    POSITIVE LOGITS
     рев
    0.06
     ölüm
    0.06
     Forums
    0.06
    ONY
    0.06
    恐
    0.06
    .Writer
    0.06
    _poll
    0.06
    .getFloat
    0.06
    .Gen
    0.06
    .Mon
    0.06
    Act Density 0.016%

    No Known Activations