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

    Neuronpedia

    INDEX
    Explanations

    support forums

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ंत
    -0.07
    SHIFT
    -0.07
    า
    -0.07
     Tut
    -0.06
     alum
    -0.06
    Alabama
    -0.06
     OL
    -0.06
     ک
    -0.06
     đậu
    -0.06
    روب
    -0.06
    POSITIVE LOGITS
    ulg
    0.06
    लब
    0.06
     Restr
    0.06
     superclass
    0.06
     publicly
    0.06
     แบบ
    0.06
    %!
    0.06
     slopes
    0.06
     BITS
    0.06
     sæ
    0.06
    Act Density 0.177%

    No Known Activations