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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Levy
    -0.09
    loot
    -0.09
    wipe
    -0.08
     anabolic
    -0.08
     Gordon
    -0.08
    osu
    -0.08
     পৌঁ
    -0.07
     santi
    -0.07
     Interstate
    -0.07
    instit
    -0.07
    POSITIVE LOGITS
    oret
    0.08
    တ
    0.08
     accent
    0.08
    丈夫
    0.07
    แข่งขัน
    0.07
     highlighted
    0.07
    此同时
    0.07
     конкур
    0.07
    이라고
    0.07
    acle
    0.07
    Act Density 0.027%

    No Known Activations