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

    Neuronpedia

    INDEX
    Explanations

    special characters or formatting elements in code or text

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

    programming keywords and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    发表于
    -0.76
    󠁿
    -0.75
    hoeddwyd
    -0.73
    rawDesc
    -0.71
    はじめに
    -0.69
    enumi
    -0.68
    endphp
    -0.68
    __*/
    -0.67
     transfieras
    -0.66
     EconPapers
    -0.65
    POSITIVE LOGITS
     Unterscheidung
    0.37
     monasterio
    0.36
     évêque
    0.35
     jueces
    0.34
     parecen
    0.33
     mismos
    0.33
     hvilke
    0.32
     novedad
    0.32
    brando
    0.31
     parecía
    0.31
    Act Density 0.036%

    No Known Activations