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

    Neuronpedia

    INDEX
    Explanations

    message context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.84
    2
    0.66
    ated
    0.63
    ot
    0.62
    ete
    0.61
    itt
    0.57
    ión
    0.57
    ney
    0.56
    arı
    0.55
    ingly
    0.55
    POSITIVE LOGITS
    a
    0.89
    f
    0.80
    મ
    0.80
    is
    0.79
    ли
    0.75
    ي
    0.75
    ه
    0.74
    ன்
    0.72
    زين
    0.70
    ת
    0.70
    Act Density 0.028%

    No Known Activations