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

    Neuronpedia

    INDEX
    Explanations

    listing items with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ประจำ
    0.65
    acula
    0.63
     assim
    0.62
    ace
    0.62
    ịp
    0.62
     कामना
    0.61
    iao
    0.60
     দুঃখ
    0.58
    vi
    0.58
     y
    0.57
    POSITIVE LOGITS
    GALAD
    0.93
     outputFile
    0.90
    郵
    0.89
     Bldg
    0.87
     vab
    0.87
    婼
    0.86
     Lag
    0.86
    嬠
    0.85
     または
    0.85
    둴
    0.84
    Act Density 0.123%

    No Known Activations