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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Animation
    -0.08
     القائمة
    -0.07
    Nun
    -0.07
     sexes
    -0.07
     symmetry
    -0.07
    (Html
    -0.07
     comprehension
    -0.07
    (indices
    -0.07
    heb
    -0.07
    ANCH
    -0.07
    POSITIVE LOGITS
     affordable
    0.10
     turnkey
    0.09
    Affordable
    0.09
     Affordable
    0.08
     rah
    0.08
     nonprofit
    0.08
     nonprofits
    0.08
     Pey
    0.08
     odre
    0.07
     solutions
    0.07
    Act Density 0.009%

    No Known Activations