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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Анд
    -0.07
     Liber
    -0.07
    _De
    -0.07
    regunta
    -0.07
    _organization
    -0.06
     Bucc
    -0.06
     ducks
    -0.06
     موتور
    -0.06
     Jos
    -0.06
    (Canvas
    -0.06
    POSITIVE LOGITS
    است
    0.06
     signs
    0.06
    )o
    0.06
    "--
    0.06
     Did
    0.06
     relaciones
    0.06
    pixels
    0.06
    이가
    0.06
     designate
    0.06
     IntelliJ
    0.06
    Act Density 0.001%

    No Known Activations