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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clerk
    -0.07
     관한
    -0.07
     canon
    -0.07
    ANA
    -0.07
    actus
    -0.06
    lower
    -0.06
    .
↵
↵
    -0.06
     bond
    -0.06
    -wheel
    -0.06
     prepaid
    -0.06
    POSITIVE LOGITS
    ,state
    0.06
    ورات
    0.06
    HostException
    0.06
    ْ
    0.06
    \Order
    0.06
    لمة
    0.06
     モ
    0.06
     ￣
    0.06
     ê
    0.06
     عص
    0.06
    Act Density 0.010%

    No Known Activations