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

    Neuronpedia

    INDEX
    Explanations

    immunity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wishlist
    -0.08
     balance
    -0.06
    ----------------------------------------------------------------------------
    -0.06
     آزمون
    -0.06
     proof
    -0.06
    ूर
    -0.06
     explaining
    -0.06
    sgi
    -0.06
     Caught
    -0.06
     Roberto
    -0.06
    POSITIVE LOGITS
     immunity
    0.10
     immune
    0.07
    imm
    0.07
    (uri
    0.06
     missionaries
    0.06
    화
    0.06
    ([^
    0.06
    альна
    0.06
    ho
    0.06
     Mongo
    0.06
    Act Density 0.001%

    No Known Activations