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

    Neuronpedia

    INDEX
    Explanations

    fill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Succ
    -0.07
     riding
    -0.06
    distributed
    -0.06
    認
    -0.06
    -radio
    -0.06
     dass
    -0.06
    requent
    -0.06
    Checkbox
    -0.06
     sexism
    -0.06
     toujours
    -0.06
    POSITIVE LOGITS
     fill
    0.08
     inflated
    0.08
     filling
    0.08
     filled
    0.07
    [((
    0.07
     airs
    0.07
     silky
    0.07
     sdf
    0.07
     joins
    0.06
     volumes
    0.06
    Act Density 0.026%

    No Known Activations