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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment

    np_max-act · gemini-2.0-flash

    The neuron activates on greeting and thank-you expressions (e.g. “Hi,” “Thank you,” “Dear …,” “thanks for …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Auction
    -0.07
     plage
    -0.07
     acomp
    -0.06
    _BUCKET
    -0.06
     basis
    -0.06
    forcing
    -0.06
     частина
    -0.06
     одним
    -0.06
    сылки
    -0.06
     fino
    -0.06
    POSITIVE LOGITS
    Oak
    0.06
     Christina
    0.06
    _SCALE
    0.06
         ↵
    0.06
    '),
↵
    0.06
    0.06
    Disposable
    0.06
    	BOOL
    0.06
    .getChildAt
    0.06
     Parm
    0.05
    Act Density 0.011%

    No Known Activations