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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Perc
    -0.07
    옥
    -0.07
    Handles
    -0.06
    yslu
    -0.06
    δρα
    -0.06
    aptic
    -0.06
    لكتر
    -0.06
    .recv
    -0.06
    비아
    -0.06
     Primer
    -0.06
    POSITIVE LOGITS
    -navbar
    0.06
     SQ
    0.06
     ра
    0.06
     Elastic
    0.06
    modal
    0.06
    ุคคล
    0.06
     hind
    0.06
    (ray
    0.06
     уд
    0.06
    =length
    0.06
    Act Density 0.048%

    No Known Activations