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

    Neuronpedia

    INDEX
    Explanations

    details/information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     urllib
    -0.07
    chemy
    -0.07
    한국
    -0.06
    чил
    -0.06
    好像
    -0.06
     Felix
    -0.06
    улю
    -0.06
    ẫn
    -0.06
     pairwise
    -0.06
     первую
    -0.06
    POSITIVE LOGITS
    (inp
    0.07
     Tod
    0.06
    ARING
    0.06
    oney
    0.06
     victory
    0.06
    tics
    0.06
    Comparison
    0.06
    bay
    0.06
     deciding
    0.06
     모두
    0.06
    Act Density 0.009%

    No Known Activations