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

    Neuronpedia

    INDEX
    Explanations

    ROC curve analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -feature
    -0.06
    Root
    -0.06
    Expect
    -0.06
    	Game
    -0.06
    Tuy
    -0.06
     begr
    -0.06
    exp
    -0.06
     clean
    -0.06
     stead
    -0.06
    appendTo
    -0.06
    POSITIVE LOGITS
    综合
    0.07
    ช
    0.07
    υπ
    0.07
    逸
    0.07
    iston
    0.06
    제
    0.06
     Nielsen
    0.06
    .Unsupported
    0.06
     interruption
    0.06
    lıklı
    0.06
    Act Density 0.008%

    No Known Activations