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

    Neuronpedia

    INDEX
    Explanations

    code-related elements, particularly focusing on punctuation and assignment operations

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

    Code snippets with operators/equals

    np_acts-logits-general · gemini-2.0-flash

    code utilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.66
     nahilalakip
    -0.66
    ьаж
    -0.60
     لينك
    -0.60
    afficheront
    -0.59
    dAtA
    -0.58
    setVerticalGroup
    -0.57
     Мексичка
    -0.57
     CallOverrides
    -0.57
    ViewImports
    -0.56
    POSITIVE LOGITS
    utils
    0.52
     utils
    0.46
    Utils
    0.38
     erop
    0.38
    util
    0.38
     Abs
    0.37
     الوطنيه
    0.35
    PAL
    0.34
     Utils
    0.33
    chio
    0.33
    Act Density 0.718%

    No Known Activations