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

    Neuronpedia

    INDEX
    Explanations

    Categorical Imperative, pittance compared

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     கண்டு
    0.42
     authorizing
    0.41
    هههه
    0.40
    ார்க
    0.39
    ম
    0.39
    ებულია
    0.38
    ভোগ
    0.38
     추출
    0.38
    冏
    0.38
    finite
    0.38
    POSITIVE LOGITS
     স্র
    0.42
     المنتج
    0.42
     Maj
    0.40
     ينا
    0.40
     Elf
    0.39
     elf
    0.38
     মাজ
    0.38
     periphery
    0.38
     Coil
    0.38
    プラグ
    0.37
    Act Density 0.000%

    No Known Activations