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

    Neuronpedia

    INDEX
    Explanations

    elements and attributes related to document manipulation and error handling in programming

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

    Code snippets using "document" or "this"

    np_acts-logits-general · gemini-2.0-flash

    code syntax prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ():
    -0.55
    ')->
    -0.55
    rungsseite
    -0.54
    сторі
    -0.51
    -0.51
    '])->
    -0.49
    ())->
    -0.49
    ")->
    -0.49
    urten
    -0.49
     "");
    -0.49
    POSITIVE LOGITS
    ['
    1.13
    [`
    1.00
     ===
    0.96
     &&
    0.95
     ['
    0.95
     !==
    0.91
    ["
    0.80
    (`${
    0.79
    ['_
    0.77
    ==='
    0.75
    Act Density 0.100%

    No Known Activations