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

    Neuronpedia

    INDEX
    Explanations

    actress, goddess, priestess

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    0.69
     entend
    0.62
     as
    0.61
     deres
    0.60
     arbejde
    0.60
     avevano
    0.59
     був
    0.57
     hadde
    0.56
    д
    0.56
    ด
    0.56
    POSITIVE LOGITS
    s
    1.12
    y
    0.86
    ،
    0.75
    )،
    0.74
    ot
    0.73
    es
    0.70
    woman
    0.70
    ol
    0.68
    um
    0.67
    inah
    0.67
    Act Density 0.027%

    No Known Activations