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

    Neuronpedia

    INDEX
    Explanations

    the curly brace characters in the code blocks

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with a whitespace character

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

    Code fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ImageContext
    -1.01
    RectangleBorder
    -1.01
     InputDecoration
    -0.86
    atase
    -0.81
    HideFlags
    -0.79
     lenker
    -0.76
    extAlignment
    -0.74
     myſelf
    -0.74
    WireFormatLite
    -0.73
    BibitemShut
    -0.73
    POSITIVE LOGITS
     «
    0.44
     
    0.44
     ma
    0.41
     im
    0.41
     I
    0.41
     ten
    0.40
     des
    0.40
     pri
    0.40
     erf
    0.39
     qu
    0.39
    Act Density 1.190%

    No Known Activations