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

    Neuronpedia

    INDEX
    Explanations

    references to instructional materials and resources

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

    sections labeled box

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteLiteral
    -0.31
    โท
    -0.29
    ódó
    -0.29
    capo
    -0.29
    archer
    -0.29
     ترم
    -0.28
     fatica
    -0.28
    IConfiguration
    -0.28
    缝
    -0.27
    DSC
    -0.27
    POSITIVE LOGITS
    Kariera
    0.54
    styleType
    0.52
     EconPapers
    0.52
    lgari
    0.51
    astéro
    0.50
     ImportError
    0.49
    IsMutable
    0.48
     swept
    0.48
     الرياضيه
    0.47
    كويكب
    0.47
    Act Density 0.317%

    No Known Activations