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

    Neuronpedia

    INDEX
    Explanations

    references to specifics and clarifications

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

    details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewInit
    -0.72
    تقاوى
    -0.71
     kasarigan
    -0.66
    󠁴
    -0.63
     INTERESAR
    -0.62
    Попис
    -0.61
    windowFixed
    -0.60
     wireType
    -0.59
     Wikimedijinoj
    -0.59
    UnusedPrivate
    -0.59
    POSITIVE LOGITS
     details
    1.59
     Details
    1.35
    details
    1.21
     DETAILS
    1.18
     detail
    1.18
    Details
    1.13
     detalles
    1.05
     detaljer
    1.05
     détails
    1.00
     Detail
    0.98
    Act Density 0.019%

    No Known Activations