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

    Neuronpedia

    INDEX
    Explanations

    calls or parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    udukan
    0.42
    anyahu
    0.38
     Schönheit
    0.37
     Gigabit
    0.36
    -)
    0.36
     Schuh
    0.36
    ience
    0.35
     الوزن
    0.35
     Фурга
    0.35
    ,...,
    0.34
    POSITIVE LOGITS
    パック
    0.45
    ropo
    0.44
    不足
    0.41
    Development
    0.40
     pak
    0.39
     lentes
    0.39
    ಡೆ
    0.38
    是不是
    0.38
    Pak
    0.38
     Pak
    0.38
    Act Density 0.000%

    No Known Activations