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

    Neuronpedia

    INDEX
    Explanations

    autoimmunity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ನೆ
    -0.09
     وس
    -0.08
    oshi
    -0.08
    نظر
    -0.08
    أما
    -0.08
    ನೇ
    -0.08
     لعب
    -0.08
    忙
    -0.08
    �
    -0.08
     Delta
    -0.08
    POSITIVE LOGITS
     autoimmune
    0.11
     violently
    0.10
     damaging
    0.09
    constitution
    0.08
     cere
    0.08
     currents
    0.08
     corrupt
    0.08
    -inflammatory
    0.08
    gred
    0.07
     corruption
    0.07
    Act Density 0.004%

    No Known Activations