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
     snake
    -0.07
    aggable
    -0.07
    爪
    -0.07
    *q
    -0.07
     ascend
    -0.06
    Guess
    -0.06
    מת
    -0.06
    련
    -0.06
    ลงทะ
    -0.06
     stroke
    -0.06
    POSITIVE LOGITS
     Semi
    0.08
    プログ
    0.07
     Anniversary
    0.07
    _ratings
    0.07
     деп
    0.07
     vinyl
    0.07
    🍰
    0.07
     Ürün
    0.07
    셜
    0.07
     policies
    0.07
    Act Density 0.003%

    No Known Activations