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

    Neuronpedia

    INDEX
    Explanations

    references to specific details or aspects pertaining to technical topics

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

    detail in code or urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     khiển
    -0.32
     także
    -0.31
     ocurrir
    -0.31
    bollah
    -0.31
    schrank
    -0.29
    Conclusie
    -0.29
    Rüyada
    -0.29
    toHaveBeen
    -0.28
     zanahoria
    -0.28
     ocurre
    -0.28
    POSITIVE LOGITS
    details
    2.78
     details
    2.59
     Details
    2.44
    detail
    2.39
    Details
    2.39
     detail
    2.16
     DETAILS
    2.09
    DETAILS
    2.08
     détails
    1.92
     Detail
    1.87
    Act Density 0.006%

    No Known Activations