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

    Neuronpedia

    INDEX
    Explanations

    виде

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     полном
    -0.09
     dispers
    -0.08
    OUCH
    -0.08
    uzz
    -0.07
    卫生
    -0.07
     Reel
    -0.07
    ೃಹ
    -0.07
     Dar
    -0.07
    QD
    -0.07
    શ્વ
    -0.07
    POSITIVE LOGITS
     Visibility
    0.08
    _pr
    0.08
    .test
    0.08
    0.08
    ygon
    0.08
     فرص
    0.07
     Belgian
    0.07
    obia
    0.07
     Guidance
    0.07
     Carlo
    0.07
    Act Density 0.002%
    No Known Activations