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

    Neuronpedia

    INDEX
    Explanations

    _size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    意见
    -0.07
     "@"
    -0.06
    _winner
    -0.06
     bourgeoisie
    -0.06
    .ButterKnife
    -0.06
     adher
    -0.06
    DateString
    -0.06
     pourrait
    -0.06
    andaş
    -0.06
    anted
    -0.06
    POSITIVE LOGITS
     explosion
    0.08
     Julius
    0.07
    atural
    0.07
     Syn
    0.06
    WEEN
    0.06
    оф
    0.06
     toxins
    0.06
     jak
    0.06
     touchscreen
    0.06
    جميع
    0.06
    Act Density 0.000%

    No Known Activations