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

    Neuronpedia

    INDEX
    Explanations

    (cache

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    що
    -0.08
    〜
    -0.07
    buttonShape
    -0.07
    rdf
    -0.06
    external
    -0.06
    task
    -0.06
    Scalar
    -0.06
    shr
    -0.06
     мати
    -0.06
    -router
    -0.06
    POSITIVE LOGITS
     Achievement
    0.07
    дат
    0.06
    ！”
    0.06
     тов
    0.06
     완
    0.06
    .med
    0.06
    /div
    0.06
     Scenes
    0.06
    (WIN
    0.06
     Sing
    0.06
    Act Density 0.000%

    No Known Activations