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

    Neuronpedia

    INDEX
    Explanations

    Research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (redis
    -0.07
     Pelosi
    -0.07
    受害者
    -0.07
    _INTER
    -0.06
     Gingrich
    -0.06
    incy
    -0.06
     hẹn
    -0.06
    Popover
    -0.06
     потеря
    -0.06
     Levy
    -0.06
    POSITIVE LOGITS
    -mode
    0.07
    Liked
    0.07
     Orion
    0.07
     southeastern
    0.07
     completo
    0.07
    _building
    0.07
    有机
    0.06
     gran
    0.06
    -b
    0.06
    奔驰
    0.06
    Act Density 0.069%

    No Known Activations