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

    Neuronpedia

    INDEX
    Explanations

    as always, as usual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ticks
    0.67
    uzie
    0.64
     derm
    0.63
    дил
    0.63
    <unused441>
    0.62
     defeats
    0.62
    бва
    0.62
     alterations
    0.61
     fittest
    0.61
    デア
    0.61
    POSITIVE LOGITS
     İş
    1.01
    Č
    0.99
    İ
    0.93
     Çalış
    0.91
    Przy
    0.90
     También
    0.89
     சில
    0.86
     öğrenc
    0.86
     trabajo
    0.86
     શિક્ષણ
    0.86
    Act Density 0.001%

    No Known Activations