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

    Neuronpedia

    INDEX
    Explanations

    occurrences of code structures and syntax elements typically found in programming languages

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

    mathematical and code symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.32
    wapV
    -0.31
     aray
    -0.29
     Observations
    -0.29
     extraction
    -0.28
    equalsIgnoreCase
    -0.28
     Public
    -0.26
    等
    -0.26
    jLabel
    -0.26
    tronlink
    -0.26
    POSITIVE LOGITS
    __":
    0.89
    __':
    0.88
     MainAxisSize
    0.72
     Roskov
    0.68
     tartalomajánló
    0.62
    expandindo
    0.61
    rungsseite
    0.60
    yarnpkg
    0.59
    ientôt
    0.59
    InitVars
    0.57
    Act Density 0.002%

    No Known Activations