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

    Neuronpedia

    INDEX
    Explanations

    hold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relations
    -0.07
     transpar
    -0.07
     બને
    -0.07
     fres
    -0.07
    서울
    -0.07
    કાર
    -0.07
     transparente
    -0.07
    .processor
    -0.07
     Transparency
    -0.07
     mot
    -0.07
    POSITIVE LOGITS
    	duration
    0.13
    _DURATION
    0.11
     muddo
    0.11
     duration
    0.11
     lasts
    0.11
    -duration
    0.11
     müdd
    0.10
    duration
    0.10
     linger
    0.10
     अवधि
    0.10
    Act Density 0.007%

    No Known Activations