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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    historical details and facts about organizations or publications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Herm
    -0.07
    /popper
    -0.06
    )v
    -0.06
     utter
    -0.06
     recurs
    -0.06
    estre
    -0.06
     physiology
    -0.06
     clothing
    -0.06
     downstairs
    -0.06
    丈夫
    -0.06
    POSITIVE LOGITS
    λίου
    0.07
    聚
    0.07
    花
    0.06
    sources
    0.06
     vez
    0.06
    нок
    0.06
    兵
    0.06
    иров
    0.06
    @gmail
    0.06
    assis
    0.06
    Act Density 0.016%

    No Known Activations