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

    Neuronpedia

    INDEX
    Explanations

    System

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adioButton
    -0.07
    ょ
    -0.06
    .dataset
    -0.06
     Chase
    -0.06
    ũng
    -0.06
    ・━・━
    -0.06
    iale
    -0.06
     Boxes
    -0.06
     Transmit
    -0.06
    тен
    -0.06
    POSITIVE LOGITS
    {(
    0.06
     -/↵
    0.06
     sat
    0.06
     مختصات
    0.06
     floor
    0.06
    お
    0.06
     affair
    0.06
     Twig
    0.06
    (report
    0.06
    ")){↵
    0.06
    Act Density 0.134%

    No Known Activations