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

    Neuronpedia

    INDEX
    Explanations

    narratives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bl
    -0.08
    -Man
    -0.07
    faith
    -0.06
    masters
    -0.06
     ordinary
    -0.06
     ZERO
    -0.06
     Collector
    -0.06
     constitutes
    -0.06
     locations
    -0.06
     depicts
    -0.06
    POSITIVE LOGITS
    iltere
    0.07
    breadcrumb
    0.07
     anlay
    0.07
    lararası
    0.06
     Çünkü
    0.06
    테
    0.06
     четвер
    0.06
    Variables
    0.06
    ה
    0.06
    .ColumnHeader
    0.06
    Act Density 0.016%

    No Known Activations