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

    Neuronpedia

    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kylie
    -0.07
    156
    -0.07
    (BitConverter
    -0.06
     поли
    -0.06
     Babylon
    -0.06
     своєї
    -0.06
     萬
    -0.06
    midd
    -0.06
    訊
    -0.06
     ترجمه
    -0.06
    POSITIVE LOGITS
     Oro
    0.07
    .tensor
    0.06
    ्रश
    0.06
    (reader
    0.06
     dann
    0.06
    Or
    0.06
    ่อไป
    0.06
    usually
    0.06
     헤
    0.06
     Its
    0.06
    Act Density 0.103%

    No Known Activations