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

    Neuronpedia

    INDEX
    Explanations

    lists of numberscode snippetsmathematical conceptsspecific events/dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.95
    ו
    0.88
    ف
    0.88
    re
    0.83
    你
    0.80
    م
    0.79
    ↵
    0.78
    ే
    0.71
    k
    0.70
    ла
    0.70
    POSITIVE LOGITS
    1.60
     a
    0.97
    3
    0.80
    이다
    0.78
    اي
    0.77
    0
    0.77
     by
    0.75
    ﻦ
    0.73
     at
    0.71
     {
    0.71
    Act Density 0.869%

    No Known Activations