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

    Neuronpedia

    INDEX
    Explanations

    data type definitions and assignments in code

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

    numerical types in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.89
     betweenstory
    -0.86
    脚注の使い方
    -0.77
    SourceChecksum
    -0.64
    msgTypes
    -0.61
    новниш
    -0.61
    awtextra
    -0.61
     Италијани
    -0.61
    -0.59
    ScopeManager
    -0.59
    POSITIVE LOGITS
    Referanser
    0.41
     <>",
    0.41
    GenerationType
    0.38
     numé
    0.34
     numerical
    0.34
    NSNumber
    0.32
     numbers
    0.32
     xuống
    0.31
    Präsident
    0.31
     évêque
    0.31
    Act Density 0.015%

    No Known Activations