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

    Neuronpedia

    INDEX
    Explanations

    Encyclopedia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >Action
    -0.07
    (Session
    -0.07
    з
    -0.06
    Sector
    -0.06
     محصول
    -0.06
    \Web
    -0.06
    urtles
    -0.06
     fate
    -0.06
     gian
    -0.06
    .Release
    -0.06
    POSITIVE LOGITS
    里面
    0.07
     subpo
    0.07
     encyclopedia
    0.07
    subscriber
    0.06
     GUID
    0.06
     Viktor
    0.06
    .dashboard
    0.06
     sched
    0.06
    _Label
    0.06
     analytics
    0.06
    Act Density 0.002%

    No Known Activations