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

    Neuronpedia

    INDEX
    Explanations

    data entry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    1.12
     እና
    0.92
    and
    0.88
    hade
    0.85
    нку
    0.84
    fice
    0.84
    hadas
    0.84
     \
    0.84
    hx
    0.84
     étapes
    0.83
    POSITIVE LOGITS
    。
    1.66
    ।
    1.41
    ı
    1.27
    .
    1.18
    ת
    1.17
    </h3>
    1.10
    ą
    1.09
    ။
    1.00
    い
    0.97
    月
    0.96
    Act Density 0.001%

    No Known Activations