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

    Neuronpedia

    INDEX
    Explanations

    instances of findings or observations related to research results

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

    found to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    انتهای
    -0.44
    yntaxException
    -0.42
    nipeg
    -0.41
     Roskov
    -0.41
     ואת
    -0.40
     Ato
    -0.39
    dehy
    -0.38
     Italijani
    -0.38
     sobriety
    -0.38
    Chy
    -0.38
    POSITIVE LOGITS
     Found
    0.94
     found
    0.92
    Found
    0.86
     FOUND
    0.71
    found
    0.71
    FOUND
    0.68
     observed
    0.61
     Observed
    0.61
     encontrado
    0.56
     ditemukan
    0.56
    Act Density 0.049%

    No Known Activations