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

    Neuronpedia

    INDEX
    Explanations

    subathon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    1.91
    finalize
    1.62
     Suppose
    1.60
     į
    1.57
    वादी
    1.54
    م
    1.50
     сделать
    1.49
    сторінку
    1.46
    ━━━━
    1.45
    ηση
    1.45
    POSITIVE LOGITS
    pped
    1.62
    -
    1.48
    y
    1.41
    粹
    1.28
    aqu
    1.27
    ulates
    1.27
    ‌تر
    1.26
    leq
    1.25
    ার
    1.24
    ppure
    1.23
    Act Density 0.185%

    No Known Activations