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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references to statistical data

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

    academic paper citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    argout
    -0.58
    pexpr
    -0.54
    Kjelder
    -0.53
    Vidite
    -0.52
     ब्रेकडाउन
    -0.49
    GTCX
    -0.48
    SourceChecksum
    -0.46
    ulsive
    -0.46
     <=",
    -0.44
     Walkover
    -0.43
    POSITIVE LOGITS
     مشين
    0.72
     للاسماء
    0.60
     EconPapers
    0.57
    PyExc
    0.50
     StatefulWidget
    0.49
    principalColumn
    0.41
    참고
    0.40
     insuffisamment
    0.39
    CrossRef
    0.39
    Grant
    0.38
    Act Density 0.058%

    No Known Activations