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

    Neuronpedia

    INDEX
    Explanations

    connected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /cli
    -0.08
    ply
    -0.08
    inct
    -0.07
    裒
    -0.07
    tract
    -0.07
    \\.
    -0.07
    赭
    -0.07
    нуть
    -0.07
    ute
    -0.07
    转基因
    -0.07
    POSITIVE LOGITS
    (byte
    0.07
     Без
    0.07
     dentro
    0.06
    っていました
    0.06
    (that
    0.06
     everytime
    0.06
     قنا
    0.06
    -direction
    0.06
     ERC
    0.06
    _empresa
    0.06
    Act Density 0.011%

    No Known Activations