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

    Neuronpedia

    INDEX
    Explanations

    percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䨐
    0.35
    䪲
    0.34
    糈
    0.33
    LuaPush
    0.33
    ുകയായിരുന്നു
    0.32
     TouchUtils
    0.32
    ↼
    0.31
    锉
    0.31
    仪式
    0.31
    激发
    0.30
    POSITIVE LOGITS
    %
    1.16
    %,
    1.05
     percent
    1.02
    %.
    1.01
    percent
    0.95
    %)
    0.94
    %:
    0.92
    %;
    0.91
    \%
    0.88
    ％
    0.86
    Act Density 0.035%

    No Known Activations