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

    Neuronpedia

    INDEX
    Explanations

    introduces or is followed by a specific item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ند
    0.57
    ه‌های
    0.49
    <unused2031>
    0.48
     Drinfeld
    0.48
     분포
    0.47
     գ
    0.46
     Bloch
    0.45
     Джо
    0.45
    奶奶
    0.45
    群众
    0.44
    POSITIVE LOGITS
    '
    0.70
    ll
    0.53
    r
    0.52
    v
    0.51
    so
    0.50
    s
    0.50
    am
    0.49
    cl
    0.48
    oval
    0.47
    <?
    0.47
    Act Density 0.002%

    No Known Activations