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

    Neuronpedia

    INDEX
    Explanations

    articles and common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ij
    0.80
     ನೆ
    0.79
     പുതിയ
    0.79
    掣
    0.79
    GOING
    0.77
     EDS
    0.77
    ਨ
    0.76
    лова
    0.76
    ル
    0.74
    lovi
    0.74
    POSITIVE LOGITS
    🏯
    0.84
    💠
    0.80
    🃏
    0.79
    #!
    0.77
     ہیں۔
    0.76
    *((
    0.75
    🎎
    0.75
     glucos
    0.73
     }}">
    0.72
    。
    0.72
    Act Density 0.000%

    No Known Activations