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

    Neuronpedia

    INDEX
    Explanations

    normalization and optimization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.62
    ssä
    1.01
    sp
    0.97
    nya
    0.93
    net
    0.92
    na
    0.89
     to
    0.88
     in
    0.87
    ll
    0.87
    ni
    0.87
    POSITIVE LOGITS
    т
    1.05
    트
    1.02
    ر
    1.02
    و
    0.99
    ي
    0.97
    зо
    0.93
    ర్
    0.91
    р
    0.90
    та
    0.90
    ર
    0.89
    Act Density 0.510%

    No Known Activations