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

    Neuronpedia

    INDEX
    Explanations

    categorized by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iest
    0.48
    i
    0.47
    o
    0.43
    ite
    0.43
     with
    0.42
     from
    0.41
     davon
    0.41
     purport
    0.41
     Also
    0.41
     to
    0.40
    POSITIVE LOGITS
     their
    0.77
     việc
    0.70
     tiga
    0.69
     тях
    0.68
     כמה
    0.66
     них
    0.63
     those
    0.63
     the
    0.63
     faptul
    0.63
     những
    0.63
    Act Density 0.329%

    No Known Activations