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

    Neuronpedia

    INDEX
    Explanations

    kindness, X, Y, fullName, year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Еще
    0.71
     ανε
    0.71
     Dateien
    0.68
    }')
    0.68
     incont
    0.66
     sonst
    0.66
     fehlen
    0.66
     assent
    0.66
     dovr
    0.66
     secretos
    0.66
    POSITIVE LOGITS
    与此同时
    0.77
    被称为
    0.77
    नावश्यक
    0.75
    ك
    0.75
    pits
    0.74
    स
    0.74
    rowski
    0.74
     \*
    0.73
    אר
    0.73
     أثناء
    0.73
    Act Density 0.003%

    No Known Activations