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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    וריה
    -0.08
    组成
    -0.08
     شن
    -0.08
    Covid
    -0.07
     основы
    -0.07
    Стоимость
    -0.07
     ori
    -0.07
    CNN
    -0.07
     стоимость
    -0.07
     inad
    -0.07
    POSITIVE LOGITS
     elegance
    0.09
     fitur
    0.08
    .Checked
    0.08
     deja
    0.08
     enlightened
    0.08
    霞
    0.07
    _features
    0.07
    _literals
    0.07
     declarations
    0.07
     enhance
    0.07
    Act Density 0.001%

    No Known Activations