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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and symbols

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on code tokens involved in declarations—especially parameter type hints and variable/member declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    antom
    -0.06
    ampton
    -0.06
     wol
    -0.06
    ίζ
    -0.06
    _orientation
    -0.06
     SPORT
    -0.06
     Sau
    -0.06
     jaw
    -0.06
    -opt
    -0.06
    -national
    -0.06
    POSITIVE LOGITS
     temiz
    0.07
    Removed
    0.07
    Alter
    0.07
    _given
    0.07
    ЎыџN
    0.07
     enerji
    0.06
    (chart
    0.06
    ;
↵
↵
↵
↵
    0.06
     gratuits
    0.06
    ?>"><?
    0.06
    Act Density 0.141%

    No Known Activations