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

    Neuronpedia

    INDEX
    Explanations

    Notification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    角色
    -0.08
     roles
    -0.08
     معم
    -0.08
     izbor
    -0.08
    بى
    -0.08
     frustrating
    -0.08
    Roles
    -0.08
     పాత్ర
    -0.08
    roles
    -0.07
    器
    -0.07
    POSITIVE LOGITS
     уведом
    0.11
    _notification
    0.09
    .Notification
    0.09
     notification
    0.09
     titled
    0.09
    (Notification
    0.09
     शीर्ष
    0.09
     оформить
    0.09
     Notification
    0.09
     alerts
    0.09
    Act Density 0.002%

    No Known Activations