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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron fires on contrastive discourse markers—words like “both,” “but,” “however,” and similar signals that indicate a comparison or contrast.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    分析
    -0.06
     grant
    -0.06
    控制
    -0.06
     grants
    -0.06
    Anonymous
    -0.06
    BILE
    -0.06
    	props
    -0.06
    _DOM
    -0.06
     maxHeight
    -0.06
    -category
    -0.06
    POSITIVE LOGITS
     indulge
    0.06
    laví
    0.06
    Textbox
    0.06
    /.
    0.06
    .getDefault
    0.06
    緒
    0.06
    geme
    0.06
    .Many
    0.06
    การแข
    0.06
     Freel
    0.06
    Act Density 0.082%

    No Known Activations