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

    Neuronpedia

    INDEX
    Explanations

    Offering or asking for help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    purple
    -0.07
     Levi
    -0.07
     Those
    -0.06
    Arg
    -0.06
    워크
    -0.06
    _doc
    -0.06
     Trev
    -0.06
    ，无
    -0.06
    ┐
    -0.06
     Direction
    -0.06
    POSITIVE LOGITS
    ερμαν
    0.06
    _CHIP
    0.06
    говор
    0.06
    ач
    0.06
    建设
    0.06
     htonl
    0.06
     }},↵
    0.06
    �
    0.06
     '{@
    0.06
    _CTL
    0.06
    Act Density 0.067%

    No Known Activations