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

    Neuronpedia

    INDEX
    Explanations

    questions with "know"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    闷
    -0.07
    place
    -0.07
    招待
    -0.07
    侵占
    -0.07
     פני
    -0.06
     ignorant
    -0.06
    攀
    -0.06
    咂
    -0.06
     attract
    -0.06
    在内的
    -0.06
    POSITIVE LOGITS
     polít
    0.08
    工艺
    0.07
     Characters
    0.07
    (TR
    0.07
    /F
    0.07
     Mg
    0.07
    olum
    0.07
     Variety
    0.07
     indust
    0.07
    extr
    0.06
    Act Density 0.030%

    No Known Activations