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

    Neuronpedia

    INDEX
    Explanations

    utf-8 encoding/decoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    it
    0.86
    ent
    0.73
     I
    0.72
    genus
    0.72
    ARMA
    0.71
    kring
    0.71
    います
    0.71
    mini
    0.68
    पणे
    0.68
    al
    0.68
    POSITIVE LOGITS
     on
    1.31
    ى
    0.98
     was
    0.83
     for
    0.82
     of
    0.79
     from
    0.79
     detenido
    0.78
    ки
    0.74
    sd
    0.73
     fueron
    0.73
    Act Density 0.009%

    No Known Activations