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

    Neuronpedia

    INDEX
    Explanations

    code punctuation and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.84
    a
    0.79
    t
    0.76
    in
    0.76
     at
    0.71
    ви
    0.70
    ა
    0.70
    (
    0.65
    фа
    0.63
    ü
    0.63
    POSITIVE LOGITS
     σε
    0.62
    و
    0.60
    ،
    0.60
    ไม่
    0.55
     ډول
    0.55
     meski
    0.54
     περιο
    0.53
    man
    0.53
     siglo
    0.53
     सार्वजनिक
    0.52
    Act Density 0.337%

    No Known Activations