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

    Neuronpedia

    INDEX
    Explanations

    typically

    np_max-act · gemini-2.0-flash

    The neuron activates on adverbs that signal generality or frequency (e.g. “typically,” “commonly,” “generally”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    <body
    -0.07
     เอ
    -0.06
    	canvas
    -0.06
    occasion
    -0.06
     forfeiture
    -0.06
     collects
    -0.06
    UTE
    -0.06
    ollision
    -0.06
    ованих
    -0.06
    eth
    -0.06
    POSITIVE LOGITS
     ticaret
    0.09
     lp
    0.07
     "__
    0.07
     defaultManager
    0.07
     好
    0.06
     tslint
    0.06
    蕉
    0.06
     güvenlik
    0.06
     下载
    0.06
     Wes
    0.06
    Act Density 0.025%

    No Known Activations