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

    Neuronpedia

    INDEX
    Explanations

    patterns of hexadecimal numbers and associated definitions

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

    Hexadecimal values

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal values and bit operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.62
     дописавши
    -0.62
    DeclareMath
    -0.56
     кӀ
    -0.55
    ngdoc
    -0.52
    UserScript
    -0.50
    $',
    -0.49
     Volkes
    -0.49
     Vikipedi
    -0.49
    colgroup
    -0.49
    POSITIVE LOGITS
    Tikang
    0.69
    rrggbb
    0.67
     jaundice
    0.64
    FF
    0.59
     Attila
    0.56
     FF
    0.56
    aarrggbb
    0.53
     Uff
    0.53
    FFFF
    0.52
     Reserved
    0.51
    Act Density 1.098%

    No Known Activations