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

    Neuronpedia

    INDEX
    Explanations

    has had

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coronavirus
    -0.10
     decades
    -0.10
    viewController
    -0.10
     Went
    -0.10
    iw
    -0.10
     subsid
    -0.09
     ticking
    -0.09
     ì½Ķë¡ľëĤĺ
    -0.09
    urum
    -0.09
    .constant
    -0.09
    POSITIVE LOGITS
     unprecedented
    0.15
     shock
    0.11
     batter
    0.11
    æļĤ
    0.11
     hit
    0.10
     ÑĥдаÑĢ
    0.10
     toll
    0.10
     Foley
    0.10
     Suspension
    0.10
     hitting
    0.10
    Act Density 0.074%

    No Known Activations