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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hold
    -0.08
    .Do
    -0.07
    ümüş
    -0.07
     thinly
    -0.06
     quần
    -0.06
     naprost
    -0.06
    kh
    -0.06
     held
    -0.06
     Ph
    -0.06
    Cost
    -0.06
    POSITIVE LOGITS
    2
    0.12
    ２
    0.08
     II
    0.07
    ูล
    0.06
     to
    0.06
    auer
    0.06
    eight
    0.06
    文章
    0.06
     Suddenly
    0.06
    ٢
    0.06
    Act Density 0.016%

    No Known Activations