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

    Neuronpedia

    INDEX
    Explanations

    rename, sequence, selfish, transfer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.61
    an
    0.53
    ad
    0.51
    i
    0.50
    ace
    0.50
    padding
    0.48
    pre
    0.48
    ing
    0.47
    ut
    0.46
    里
    0.46
    POSITIVE LOGITS
    ным
    0.58
    פ
    0.54
     magní
    0.50
     நாள்
    0.50
    шений
    0.48
    َى
    0.48
     banal
    0.47
    ے
    0.47
    ඪ
    0.47
     cuya
    0.47
    Act Density 0.000%

    No Known Activations