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

    Neuronpedia

    INDEX
    Explanations

    words related to instructions and technical details

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

    LaTeX math environment

    np_acts-logits-general · gemini-2.0-flash

    LaTeX math and code files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.48
    -0.48
    ʺ
    -0.46
    -0.46
    чан
    -0.46
    -0.44
    -0.44
     domain
    -0.43
    -0.43
    -0.43
    POSITIVE LOGITS
     itſelf
    1.11
    Datuak
    1.06
     مشين
    1.03
     Anſ
    1.03
     myſelf
    0.99
     Theſe
    0.98
     дописавши
    0.96
     Reſ
    0.96
     Diſ
    0.95
     NSCoder
    0.95
    Act Density 0.020%

    No Known Activations