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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific paths or configurations in code

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

    file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eynman
    -0.46
    hobia
    -0.41
     אפ
    -0.40
    Ẳ
    -0.40
     Mussolini
    -0.40
    onedDateTime
    -0.40
     Bili
    -0.39
     superstition
    -0.38
    ční
    -0.38
     copyright
    -0.38
    POSITIVE LOGITS
     للاسماء
    0.65
    تقاوى
    0.52
    %/
    0.49
    ngdoc
    0.48
    richTextPanel
    0.47
     Meksiku
    0.47
    RenderAtEndOf
    0.47
    Personendaten
    0.46
     ExecuteAsync
    0.44
    °/
    0.44
    Act Density 0.048%

    No Known Activations