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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of punctuation marks or symbols in programming and coding contexts

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

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zijne
    -0.48
     mijne
    -0.40
     Bewußt
    -0.39
     Erwä
    -0.38
     Einfluß
    -0.38
     honneur
    -0.37
     useRef
    -0.35
    LookAnd
    -0.34
    }-*/;
    -0.34
     köp
    -0.34
    POSITIVE LOGITS
     CURIAM
    0.61
    UVWXYZ
    0.56
    таратура
    0.48
    MIDDLEWARE
    0.47
    ご馳走
    0.46
    ements
    0.45
     Aval
    0.45
     initComponents
    0.45
    tyard
    0.45
    FormTagHelper
    0.45
    Act Density 0.035%

    No Known Activations