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

    Neuronpedia

    INDEX
    Explanations

    technical terms and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ců
    0.41
    ၿ
    0.38
    ၷ
    0.37
    佽
    0.37
    নর
    0.36
     tubules
    0.34
    퐫
    0.34
    zgl
    0.34
     ставки
    0.34
     oun
    0.34
    POSITIVE LOGITS
     not
    0.37
    udas
    0.37
     no
    0.36
     ignore
    0.35
     أيضاً
    0.35
     misguided
    0.34
     не
    0.34
     Ignore
    0.34
     לא
    0.34
    е
    0.33
    Act Density 0.013%

    No Known Activations