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

    Neuronpedia

    INDEX
    Explanations

    cdot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .nan
    -0.07
    .Predicate
    -0.07
     charged
    -0.06
    .Rendering
    -0.06
     Broncos
    -0.06
    加盟店
    -0.06
    ไทย
    -0.06
     عنه
    -0.06
    (cljs
    -0.06
     pré
    -0.06
    POSITIVE LOGITS
    社会发展
    0.08
     Chow
    0.07
     Bowling
    0.07
    調
    0.07
     stuff
    0.07
    usz
    0.07
    Diff
    0.07
    This
    0.07
    .match
    0.07
    共创
    0.07
    Act Density 0.001%

    No Known Activations