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

    Neuronpedia

    INDEX
    Explanations

    you so

    np_max-act · gemini-2.0-flash

    The neuron activates on the modal verb “can” (and its immediate context indicating ability or possibility).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     './../
    -0.06
    igate
    -0.06
    폰
    -0.06
    actory
    -0.06
    уже
    -0.06
    -power
    -0.06
     doorstep
    -0.06
     Sleeve
    -0.06
    Coach
    -0.06
    _resolve
    -0.05
    POSITIVE LOGITS
     so
    0.12
     an
    0.08
     SO
    0.07
     슈
    0.07
    so
    0.07
     BK
    0.07
     remarked
    0.07
    �
    0.07
    	ar
    0.07
     revital
    0.06
    Act Density 0.073%

    No Known Activations