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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ープ
    -0.07
    film
    -0.06
    .endswith
    -0.06
    まず
    -0.06
    گل
    -0.06
     фак
    -0.06
     stabilization
    -0.06
    Crop
    -0.06
    �
    -0.06
    slu
    -0.06
    POSITIVE LOGITS
    ология
    0.06
    _ENCODE
    0.06
     Bài
    0.06
    _gettime
    0.06
     آینده
    0.06
     Ülke
    0.06
    想要
    0.06
     �
    0.06
    óc
    0.06
     Adjustable
    0.06
    Act Density 0.010%

    No Known Activations