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

    Neuronpedia

    INDEX
    Explanations

    elements of structured programming syntax and data structures commonly found in code

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

    Code, math, or special characters

    np_acts-logits-general · gemini-2.0-flash

    code delimiters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -1.10
    InputBorder
    -1.10
    enumi
    -1.09
    NUMX
    -1.08
     GIPHY
    -1.06
     كومونز
    -1.06
    BufferException
    -1.05
     iſt
    -1.03
    AnimationsModule
    -1.00
     arşivlendi
    -1.00
    POSITIVE LOGITS
     (
    1.16
     
    1.16
    ,
    1.05
     "
    1.04
     a
    0.94
     -
    0.92
    .
    0.91
    ↵↵
    0.90
    ↵
    0.89
    :
    0.88
    Act Density 2.750%

    No Known Activations