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

    Neuronpedia

    INDEX
    Explanations

    mic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tied
    -0.07
     avenue
    -0.07
    挺
    -0.07
    笪
    -0.07
    💘
    -0.07
     hunts
    -0.06
    NING
    -0.06
    يدي
    -0.06
    isel
    -0.06
    ╊
    -0.06
    POSITIVE LOGITS
     illness
    0.07
     والع
    0.07
    命令
    0.07
     iht
    0.07
    一句话
    0.07
    application
    0.07
    大妈
    0.07
    =all
    0.07
    iring
    0.07
    _tr
    0.07
    Act Density 0.000%

    No Known Activations