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

    Neuronpedia

    INDEX
    Explanations

    percentages of a whole

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sinh
    0.40
    Entry
    0.39
    anigans
    0.39
    Sinh
    0.38
    essoa
    0.38
    วัฒ
    0.38
    Endian
    0.37
    มากมาย
    0.37
    aleph
    0.36
    Citizens
    0.36
    POSITIVE LOGITS
     percent
    1.25
     (%)
    1.16
    percent
    1.06
    %,
    0.98
     процентов
    0.97
     (\%)
    0.96
    %)
    0.94
     procent
    0.93
    ％
    0.93
     Percent
    0.93
    Act Density 0.045%

    No Known Activations