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

    Neuronpedia

    INDEX
    Explanations

    function with argument "distance"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Derrick
    0.43
    বলী
    0.42
     Prerequisites
    0.41
     Cyber
    0.41
     सहज
    0.40
    烩
    0.39
    Woo
    0.39
     KISS
    0.39
     Immediately
    0.39
     canlı
    0.39
    POSITIVE LOGITS
    พวกเขา
    0.48
    는
    0.45
    ०
    0.43
    국
    0.40
     milioane
    0.40
    솔
    0.40
    0
    0.39
    규
    0.39
    нага
    0.39
    ם
    0.39
    Act Density 0.002%

    No Known Activations