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

    Neuronpedia

    INDEX
    Explanations

    reporter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ฆ
    -0.08
     lập
    -0.07
    چھ
    -0.07
    ��
    -0.07
    announcement
    -0.07
    obs
    -0.07
    stay
    -0.07
     हट
    -0.07
     Appearance
    -0.07
    不要
    -0.07
    POSITIVE LOGITS
     Waren
    0.10
     الكرة
    0.09
     پروژه
    0.08
     Вост
    0.08
     បាន
    0.08
     任
    0.08
    )o
    0.08
     reporter
    0.08
    (Il
    0.08
    ાવવામાં
    0.08
    Act Density 0.001%

    No Known Activations