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

    Neuronpedia

    INDEX
    Explanations

    normal, healthy, okay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Τα
    0.41
     Lesley
    0.40
    assertSame
    0.39
    Tang
    0.38
    ระยะ
    0.38
     måtte
    0.37
     मिलेंगे
    0.37
    Τα
    0.37
     sélectionnez
    0.36
    唐
    0.36
    POSITIVE LOGITS
     harmless
    0.88
     legitimate
    0.79
     legitimately
    0.79
    正常的
    0.74
     legít
    0.71
     innocuous
    0.69
     legitt
    0.66
     нормально
    0.65
     normal
    0.64
     healthy
    0.64
    Act Density 0.141%

    No Known Activations