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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ContainerGap
    -0.07
    Wie
    -0.07
     lớp
    -0.07
     до
    -0.06
    enthal
    -0.06
     Relative
    -0.06
     yönelik
    -0.06
    柳
    -0.06
     religious
    -0.06
     JButton
    -0.06
    POSITIVE LOGITS
    کت
    0.08
    rocess
    0.07
    ublik
    0.07
    pkt
    0.06
    neck
    0.06
     будь
    0.06
     BALL
    0.06
    _version
    0.06
    (ball
    0.06
     تهران
    0.06
    Act Density 0.057%

    No Known Activations