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

    Neuronpedia

    INDEX
    Explanations

    legal rulings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    飾
    -0.06
     Schmidt
    -0.06
     rental
    -0.06
     Helena
    -0.06
     نیرو
    -0.06
     مهند
    -0.06
     Tribunal
    -0.06
    ！
    -0.06
     남자
    -0.06
     Venice
    -0.06
    POSITIVE LOGITS
    اء
    0.07
     vitamins
    0.07
    OK
    0.07
     unaware
    0.06
    ANNER
    0.06
    <object
    0.06
    .getSelection
    0.06
     logic
    0.06
    .address
    0.06
     Corn
    0.06
    Act Density 0.008%

    No Known Activations