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

    Neuronpedia

    INDEX
    Explanations

    `data` class constructor enum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    1.72
    ب
    1.34
    ل
    1.23
    ્સ
    1.20
    例如
    1.20
    \,\
    1.19
    بق
    1.17
    きた
    1.14
    1.13
    بدا
    1.12
    POSITIVE LOGITS
     sacram
    1.38
    fass
    1.32
     Infrast
    1.27
     Stur
    1.26
    le
    1.24
     ants
    1.23
     Cliente
    1.22
     Titans
    1.21
     breweries
    1.20
    urers
    1.20
    Act Density 0.000%

    No Known Activations