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

    Neuronpedia

    INDEX
    Explanations

    various types of syntax or formatting used in programming or mathematical expressions

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

    LaTeX code or mathematical formulas

    np_acts-logits-general · gemini-2.0-flash

    invalid argument exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.66
    ↵↵↵
    -0.60
     ’
    -0.59
     col
    -0.56
    vikle
    -0.56
     ~
    -0.54
     par
    -0.54
     restos
    -0.54
     fast
    -0.54
     high
    -0.54
    POSITIVE LOGITS
     Sodom
    1.07
    theless
    0.95
     Ather
    0.92
     Rhy
    0.90
     apothe
    0.88
    __':
    0.86
    DeleteBehavior
    0.86
     Khrushchev
    0.86
     loch
    0.85
     getItemId
    0.85
    Act Density 0.002%

    No Known Activations