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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    finite
    -0.07
     rectangle
    -0.06
    ่อส
    -0.06
    اسطة
    -0.06
     rave
    -0.06
    _revision
    -0.06
    _FACTOR
    -0.06
    .Tween
    -0.06
    _ra
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Alman
    0.07
    titulo
    0.06
    (tokens
    0.06
     murky
    0.06
     Below
    0.06
     cookies
    0.06
     madrid
    0.06
     d
    0.06
    ์ล
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations