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

    Neuronpedia

    INDEX
    Explanations

    wisdom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _none
    -0.07
    ابط
    -0.06
     cul
    -0.06
     jealous
    -0.06
    -INF
    -0.06
    		    ↵
    -0.06
     brigade
    -0.06
    /google
    -0.06
     inference
    -0.06
    INTERNAL
    -0.06
    POSITIVE LOGITS
     ル
    0.08
     hodně
    0.06
     德
    0.06
     homophobic
    0.06
     unfortunate
    0.06
     비
    0.06
     اگر
    0.06
    .');↵↵
    0.06
    .GetKey
    0.06
    .nextDouble
    0.06
    Act Density 0.000%

    No Known Activations