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

    Neuronpedia

    INDEX
    Explanations

    competitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jede
    -0.07
    same
    -0.07
     طی
    -0.06
    /pdf
    -0.06
     trị
    -0.06
    移
    -0.06
     maté
    -0.06
    socket
    -0.06
    peč
    -0.06
     bpp
    -0.06
    POSITIVE LOGITS
     Ronnie
    0.07
     ш
    0.07
     oku
    0.06
     нас
    0.06
    Bins
    0.06
    ublic
    0.06
    -auto
    0.06
    Instances
    0.06
    Entries
    0.06
     Upper
    0.06
    Act Density 0.017%

    No Known Activations