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

    Neuronpedia

    INDEX
    Explanations

    asking to do something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    activex
    -0.07
    _boolean
    -0.07
    死角
    -0.07
    urved
    -0.07
    技术支持
    -0.06
    ensored
    -0.06
    -bordered
    -0.06
    _tac
    -0.06
    .sep
    -0.06
    -house
    -0.06
    POSITIVE LOGITS
     shifts
    0.08
    Wh
    0.08
    胎儿
    0.07
     Из
    0.07
    睡
    0.07
    亚太
    0.07
    都
    0.07
    /usr
    0.07
     cet
    0.07
     tens
    0.07
    Act Density 0.119%

    No Known Activations