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

    Neuronpedia

    INDEX
    Explanations

    adopted

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens, especially decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     streets
    -0.07
     mismo
    -0.07
    	printk
    -0.07
     sentences
    -0.06
     hemen
    -0.06
    İS
    -0.06
     ylim
    -0.06
     protr
    -0.06
    .mult
    -0.06
    _subs
    -0.06
    POSITIVE LOGITS
    ніше
    0.07
     返回
    0.06
    /layout
    0.06
     getResource
    0.06
     microsoft
    0.06
    erspective
    0.06
     Advertising
    0.06
     ")↵↵
    0.06
    _com
    0.06
     ثبت
    0.06
    Act Density 0.227%

    No Known Activations