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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates or events, particularly related to historical contexts

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

    historical years 1942, 1943, 1944

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    自
    -0.40
    {}/
    -0.40
    nutí
    -0.39
    ENDS
    -0.38
     Michaela
    -0.38
    andolo
    -0.37
     exclusivity
    -0.37
     satunya
    -0.37
    erà
    -0.37
    bindet
    -0.37
    POSITIVE LOGITS
    DIPSETTING
    0.63
    发表于
    0.63
     فريبيس
    0.61
     препратки
    0.59
     kasarigan
    0.57
    Viitteet
    0.57
     المعيارى
    0.57
    WithIOException
    0.57
    Hitler
    0.56
     ModelExpression
    0.55
    Act Density 0.022%

    No Known Activations