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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron activates on punctuation marks—especially quotation marks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    --*/↵
    -0.07
     Lew
    -0.07
    _fig
    -0.07
    gable
    -0.07
     Gale
    -0.07
    90
    -0.06
    getStatus
    -0.06
    cury
    -0.06
     amateurs
    -0.06
     RET
    -0.06
    POSITIVE LOGITS
    	socket
    0.07
    declspec
    0.06
     entwick
    0.06
     تجربه
    0.06
     sık
    0.06
     aseg
    0.06
     폭
    0.06
    	strcpy
    0.06
     liên
    0.06
    连接
    0.06
    Act Density 0.036%

    No Known Activations