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
    ⓤ
    -0.09
    ₠
    -0.07
    .SelectedValue
    -0.07
    原标题
    -0.07
    ﹁
    -0.06
     headache
    -0.06
    耇
    -0.06
     чего
    -0.06
    එ
    -0.06
    ℮
    -0.06
    POSITIVE LOGITS
    YTE
    0.08
     lia
    0.08
    dy
    0.08
    prints
    0.08
    General
    0.07
    CR
    0.07
     قامت
    0.07
     Girls
    0.07
    Lee
    0.07
     женщин
    0.07
    Act Density 0.016%

    No Known Activations