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

    Neuronpedia

    INDEX
    Explanations

    distinct patterns or structures within programming or markup syntax

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

    code structures and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.80
    JoinColumn
    -0.56
     pyplot
    -0.55
     Schoen
    -0.54
    autoreleasepool
    -0.54
     whilst
    -0.53
     입니다
    -0.52
    NOPQRST
    -0.50
    Javascript
    -0.50
     Javascript
    -0.50
    POSITIVE LOGITS
     Corbin
    0.52
     Houſe
    0.48
    iações
    0.47
     cœurs
    0.47
    sizable
    0.46
     mariscos
    0.46
    imdi
    0.46
    neſs
    0.46
    ſelf
    0.46
     Lazio
    0.46
    Act Density 0.075%

    No Known Activations