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

    Neuronpedia

    INDEX
    Explanations

    sequential formatting or structural elements within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code and structured data markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.48
     kasarigan
    -0.45
     للمعارف
    -0.45
     Natal
    -0.44
    ніципа
    -0.43
    godic
    -0.43
    Natal
    -0.43
     castor
    -0.43
    natal
    -0.42
    enital
    -0.41
    POSITIVE LOGITS
    FunctionFlags
    0.44
    Grüsse
    0.43
     muligt
    0.42
    RTLD
    0.41
     ouvriers
    0.41
     ब्रेकडाउन
    0.39
    İstinadlar
    0.39
     noiva
    0.39
    EDEFAULT
    0.38
     senhora
    0.38
    Act Density 0.002%

    No Known Activations