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

    Neuronpedia

    INDEX
    Explanations

    syntactic elements and control structures commonly used in programming languages

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

    Code-related punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    code diffs and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.54
    enumi
    -0.50
    Atsauces
    -0.50
    Viited
    -0.49
    🏽
    -0.49
    🏾
    -0.48
    jock
    -0.47
    ٬
    -0.47
    تيجة
    -0.47
     haem
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.68
     Lightboxes
    0.61
    abestanden
    0.60
    енча
    0.57
     Paix
    0.57
    parsedMessage
    0.56
     nawr
    0.56
     kaarangay
    0.55
    cokinetic
    0.54
     CJK
    0.54
    Act Density 0.120%

    No Known Activations