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

    Neuronpedia

    INDEX
    Explanations

    specific programming keywords and syntax elements

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

    Tokens after certain signal names (SIG) or keywords

    np_acts-logits-general · gemini-2.0-flash

    programming keywords and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fût
    -0.85
     itſelf
    -0.77
     myſelf
    -0.77
     iſt
    -0.74
     Monfieur
    -0.70
     Jefus
    -0.69
     ―――――
    -0.69
     Theſe
    -0.68
     commerciaux
    -0.67
     faſt
    -0.66
    POSITIVE LOGITS
    aarrggbb
    0.66
    instancetype
    0.63
    nameof
    0.58
     nameof
    0.57
    databind
    0.57
     "));
    0.55
    "));
    0.55
     servic
    0.54
    期刊论文
    0.51
     sho
    0.51
    Act Density 0.687%

    No Known Activations