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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash

    This neuron fires on programming‐language syntax tokens—keywords, operators, punctuation marks, and other code symbols.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ((-
    -0.06
    сок
    -0.06
    classnames
    -0.06
     moderated
    -0.06
    })();
    -0.06
    Sites
    -0.06
    十二
    -0.05
    ']."
    -0.05
    LinkedList
    -0.05
    elidir
    -0.05
    POSITIVE LOGITS
     Upon
    0.07
     colour
    0.07
     heavyweight
    0.07
    ルの
    0.07
     tournament
    0.07
    _theme
    0.06
     agreed
    0.06
     hodnoty
    0.06
    fal
    0.06
     Guidelines
    0.06
    Act Density 0.008%

    No Known Activations