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

    Neuronpedia

    INDEX
    Explanations

    scientific studies and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chose
    -0.07
    Kate
    -0.07
     Нат
    -0.06
     Кур
    -0.06
    Victoria
    -0.06
     Acc
    -0.06
    遣
    -0.06
    ्रपत
    -0.06
    W
    -0.06
     Grammy
    -0.06
    POSITIVE LOGITS
    ..↵
    0.07
    _gener
    0.07
    حيح
    0.07
    >(
    0.07
    alsex
    0.06
     richTextBox
    0.06
    /package
    0.06
    cov
    0.06
     strtok
    0.06
     文件
    0.06
    Act Density 0.055%

    No Known Activations