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

    Neuronpedia

    INDEX
    Explanations

    proverb or saying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.68
    ला
    0.63
    ड
    0.56
    u
    0.54
     university
    0.53
    ले
    0.52
    ម
    0.49
    ла
    0.49
     holog
    0.49
     terapi
    0.49
    POSITIVE LOGITS
    っぽ
    0.60
    贫
    0.57
    ѕ
    0.57
    ъ
    0.55
    òn
    0.54
    жуть
    0.52
    يدة
    0.52
    ிகள்
    0.51
    제목
    0.51
    Những
    0.51
    Act Density 0.012%

    No Known Activations