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

    Neuronpedia

    INDEX
    Explanations

    cold and warmth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (display
    -0.07
     Guang
    -0.07
    특별
    -0.06
    ointments
    -0.06
     Growth
    -0.06
    _FL
    -0.06
    .gradient
    -0.06
    YPRE
    -0.06
    Leading
    -0.06
     OAuth
    -0.06
    POSITIVE LOGITS
    باح
    0.06
    زاده
    0.06
     рахунок
    0.06
    Ln
    0.06
     dựng
    0.06
     cold
    0.06
    .IC
    0.06
     skirm
    0.06
    ím
    0.06
     extremes
    0.06
    Act Density 0.220%

    No Known Activations