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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	array
    -0.07
     hostel
    -0.07
    	diff
    -0.07
     transparency
    -0.07
    Foundation
    -0.07
    高尚
    -0.07
    Disp
    -0.07
     thị
    -0.07
    嚎
    -0.07
    nor
    -0.06
    POSITIVE LOGITS
    �
    0.07
    .removeAll
    0.07
     deepest
    0.07
    آل
    0.06
    éli
    0.06
     Marine
    0.06
     advertisers
    0.06
    能耗
    0.06
     weakening
    0.06
    \.
    0.06
    Act Density 0.007%

    No Known Activations