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

    Neuronpedia

    INDEX
    Explanations

    punctuation and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consectetur
    -0.07
    -gray
    -0.07
     Hive
    -0.07
    ereum
    -0.07
    glyphicon
    -0.06
    isicing
    -0.06
    toHave
    -0.06
     glVertex
    -0.06
    getSingleton
    -0.06
    .setWindowTitle
    -0.06
    POSITIVE LOGITS
    体力
    0.08
    Did
    0.07
    (pred
    0.07
    -minded
    0.07
    军人
    0.07
     threatened
    0.07
    Delivery
    0.07
    .cost
    0.06
    pred
    0.06
    تحر
    0.06
    Act Density 0.013%

    No Known Activations