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

    Neuronpedia

    INDEX
    Explanations

    ran

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ویژ
    -0.07
    ebiliriz
    -0.07
    遭
    -0.06
    urga
    -0.06
     interception
    -0.06
     Parse
    -0.06
    Raw
    -0.06
    isí
    -0.06
    地球
    -0.06
     UNU
    -0.06
    POSITIVE LOGITS
     Gomez
    0.07
     distr
    0.06
     he
    0.06
     /\
    0.06
     Contents
    0.06
     distances
    0.06
    аф
    0.06
     cave
    0.06
    .af
    0.06
     strate
    0.06
    Act Density 0.017%

    No Known Activations