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

    Neuronpedia

    INDEX
    Explanations

    years and decades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وة
    0.95
     abiding
    0.93
     screech
    0.89
    national
    0.88
    0.87
     refrain
    0.86
     carriage
    0.86
    ۢ
    0.86
    yoga
    0.86
    zé
    0.84
    POSITIVE LOGITS
     LikeLike
    0.92
    Empleado
    0.89
     Broadcast
    0.88
     kiuj
    0.88
     Raul
    0.85
     சென்று
    0.84
    पटना
    0.83
     Sección
    0.81
    σσ
    0.81
     Otra
    0.80
    Act Density 0.024%

    No Known Activations