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

    Neuronpedia

    INDEX
    Explanations

    the number 1 followed by another digit

    oai_token-act-pair · gemini-2.0-flash

    technical code elements or identifiers

    np_token-act-pair-logits · gpt-4o-mini

    Number 1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     &
    -0.59
     Bo
    -0.58
     bo
    -0.55
    &
    -0.54
    bo
    -0.54
     va
    -0.50
     
    -0.50
     F
    -0.49
    (&
    -0.48
     geslacht
    -0.48
    POSITIVE LOGITS
    +#+#
    0.93
     فريبيس
    0.87
     AssemblyCulture
    0.81
    RegistryLite
    0.77
    ValueStyle
    0.76
    AutoScaleMode
    0.75
    tagHelperRunner
    0.73
    ThroughAttribute
    0.73
    oredCriteria
    0.71
    aarrggbb
    0.70
    Act Density 1.030%

    No Known Activations