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

    Neuronpedia

    INDEX
    Explanations

    qualities of voice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bhagavato
    0.68
     lézards
    0.67
     yattha
    0.65
     dilwale
    0.64
     saludables
    0.64
     pensato
    0.63
     ciekaw
    0.63
     pensamientos
    0.62
     atentos
    0.62
     labbhati
    0.61
    POSITIVE LOGITS
     voice
    0.80
    voice
    0.75
    de
    0.71
    D
    0.70
    s
    0.68
     de
    0.68
     of
    0.67
    d
    0.66
     as
    0.63
    not
    0.62
    Act Density 0.037%

    No Known Activations