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

    Neuronpedia

    INDEX
    Explanations

    hyphens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kansas
    -0.07
     Democrat
    -0.07
     Physics
    -0.07
     Peru
    -0.06
    opathy
    -0.06
     marty
    -0.06
    าณาจ
    -0.06
     العلم
    -0.06
    ayas
    -0.06
     Turkey
    -0.06
    POSITIVE LOGITS
    istle
    0.06
    /software
    0.06
     المدر
    0.06
    -ли
    0.06
     '''
↵
    0.06
    _POST
    0.05
     massasje
    0.05
    ('@
    0.05
     richTextBox
    0.05
     );↵↵
    0.05
    Act Density 0.001%

    No Known Activations