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

    Neuronpedia

    INDEX
    Explanations

    DIST

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tray
    -0.08
    range
    -0.08
    vid
    -0.08
     abl
    -0.07
    첧
    -0.07
     prove
    -0.07
    etch
    -0.07
    oplay
    -0.07
     escapes
    -0.07
     Zap
    -0.07
    POSITIVE LOGITS
    뒹
    0.08
    んだろう
    0.08
    但是
    0.07
    רכש
    0.07
     pierws
    0.07
    더라
    0.07
    떪
    0.07
    خيص
    0.07
    mız
    0.07
    묜
    0.07
    Act Density 0.001%

    No Known Activations