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

    Neuronpedia

    INDEX
    Explanations

    watch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מדה
    -0.07
     skillet
    -0.07
    還沒
    -0.07
    נוער
    -0.07
    המל
    -0.07
    ước
    -0.07
    侠
    -0.07
    xffff
    -0.07
    反正
    -0.07
    โย
    -0.07
    POSITIVE LOGITS
    lose
    0.07
     событи
    0.07
    REF
    0.07
    Ship
    0.07
    _prob
    0.07
    token
    0.07
    prob
    0.07
    _interval
    0.07
     They
    0.07
    感
    0.07
    Act Density 0.012%

    No Known Activations