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

    Neuronpedia

    INDEX
    Explanations

    references to GitHub URLs or related commands

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

    Code import statements with file paths

    np_acts-logits-general · gemini-2.0-flash

    code repository paths and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.49
     item
    -0.45
     مشين
    -0.43
    >>>>
    -0.40
    u
    -0.40
     blieb
    -0.40
    ponses
    -0.39
    uv
    -0.39
    ».
    -0.39
     isim
    -0.39
    POSITIVE LOGITS
    Билгалдахарш
    0.91
     فريبيس
    0.87
    ########.
    0.82
     незавершена
    0.78
    extAlignment
    0.77
    KURZBESCHREIBUNG
    0.75
    RenderAtEndOf
    0.71
     purpoſe
    0.71
    Pautan
    0.71
     >=",
    0.70
    Act Density 0.031%

    No Known Activations