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

    Neuronpedia

    INDEX
    Explanations

    references to programming packages and Python modules

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

    file paths and code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desconocido
    -0.40
     Protección
    -0.38
     contemporáneo
    -0.38
     portavoz
    -0.36
     recuperación
    -0.35
     recientemente
    -0.34
    :+:
    -0.34
     semejante
    -0.33
     exclusiva
    -0.33
     representación
    -0.32
    POSITIVE LOGITS
    /**
    0.77
    Билгалдахарш
    0.59
    WireFormatLite
    0.58
    aarrggbb
    0.56
    rungsseite
    0.56
    iſen
    0.55
     CreateTagHelper
    0.53
    FunctionFlags
    0.53
    ScopeManager
    0.52
    MigrationBuilder
    0.51
    Act Density 0.003%

    No Known Activations