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

    Neuronpedia

    INDEX
    Explanations

    robotic arms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    টন
    0.43
    elevator
    0.42
    قى
    0.41
    История
    0.40
    Elder
    0.38
    Neue
    0.38
    occupied
    0.38
     viele
    0.38
     elevator
    0.38
    शब्द
    0.38
    POSITIVE LOGITS
     Фор
    0.44
    రా
    0.43
    φορά
    0.43
     PPE
    0.43
     Ζ
    0.42
     পুরুষ
    0.42
    枃
    0.41
     forfe
    0.41
    pointA
    0.41
     பார
    0.41
    Act Density 0.000%

    No Known Activations