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
    сок
    -0.07
     iris
    -0.06
     cone
    -0.06
    hi
    -0.06
    stance
    -0.06
    ら
    -0.06
    ě
    -0.06
     motto
    -0.06
    ιν
    -0.06
    nů
    -0.06
    POSITIVE LOGITS
    责任
    0.06
    [{
    0.06
     fireworks
    0.06
    .ToDouble
    0.06
    بی
    0.06
     відбу
    0.06
    _FL
    0.06
     mage
    0.06
    ีผ
    0.06
    LayoutParams
    0.06
    Act Density 0.008%

    No Known Activations