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

    Neuronpedia

    INDEX
    Explanations

    references to logging and error handling in code

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

    log and debug messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.78
     ब्रेकडाउन
    -0.75
     للمعارف
    -0.73
    InjectAttribute
    -0.73
    tagHelperRunner
    -0.73
     ujednoznacz
    -0.71
    帖最后由
    -0.71
     Chwiliwch
    -0.69
    :✨
    -0.69
    ValueStyle
    -0.67
    POSITIVE LOGITS
    भ
    0.35
     l
    0.33
    l
    0.32
     sp
    0.30
    0.30
    berichte
    0.30
    ah
    0.30
    中
    0.29
    dis
    0.29
    e
    0.29
    Act Density 0.003%
    No Known Activations