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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or symbols used in programming code

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

    `<start_of_turn> user`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.63
    ThroughAttribute
    -0.60
     <<<<<<<<<<<<<<
    -0.57
    AnchorTagHelper
    -0.57
    RegressionTest
    -0.56
    onViewCreated
    -0.56
    новниш
    -0.53
    LookAnd
    -0.53
     '\\;'
    -0.51
    onActivityResult
    -0.50
    POSITIVE LOGITS
    HEET
    0.46
     olmayan
    0.44
     uſed
    0.41
    deed
    0.39
    rsiniz
    0.39
    orexia
    0.39
    sheet
    0.39
    Sheet
    0.39
    heet
    0.39
     BD
    0.38
    Act Density 0.002%

    No Known Activations