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
    دم
    -0.07
    ných
    -0.06
    _extra
    -0.06
    _quit
    -0.06
    label
    -0.06
    调
    -0.06
     Songs
    -0.06
    ation
    -0.06
     ly
    -0.06
     foods
    -0.06
    POSITIVE LOGITS
     asi
    0.06
     정규
    0.06
     zajímav
    0.06
    （笑
    0.06
    HOW
    0.06
     Вот
    0.06
                
    0.06
    0.06
    ви
    0.06
    Ｏ
    0.06
    Act Density 0.035%

    No Known Activations