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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UNICODE
    -0.07
    �
    -0.07
    问询
    -0.07
    assert
    -0.07
    ágenes
    -0.07
    🐓
    -0.07
    Activities
    -0.06
     apl
    -0.06
     iter
    -0.06
    chapter
    -0.06
    POSITIVE LOGITS
    发作
    0.07
    enses
    0.07
    orgeous
    0.06
    ressive
    0.06
     своим
    0.06
     całej
    0.06
     Flower
    0.06
    French
    0.06
    ga
    0.06
    uous
    0.06
    Act Density 0.002%

    No Known Activations