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

    Neuronpedia

    INDEX
    Explanations

    markdown-like formatting and structure elements in the text

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

    Mathematical symbols, especially dots, hyphens, and caps

    np_acts-logits-general · gemini-2.0-flash

    formatting and list separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.82
     "..\..\..\
    -0.76
    '])->
    -0.72
     ?>/
    -0.71
     Italijanski
    -0.71
    ']],
    -0.70
    '):
    -0.67
    ')));
    -0.67
    fromnode
    -0.65
    うちに
    -0.65
    POSITIVE LOGITS
     Potsdam
    0.65
     تضيفلها
    0.64
     epistle
    0.63
    itemize
    0.62
     febri
    0.60
    DMETHOD
    0.59
     Boun
    0.57
     shrou
    0.56
    RectangleBorder
    0.56
    StringVar
    0.55
    Act Density 0.005%

    No Known Activations