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

    Neuronpedia

    INDEX
    Explanations

    emphasis with asterisks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Olá
    0.49
    Silicon
    0.44
    Zitat
    0.43
     durable
    0.42
     여행
    0.42
     thiện
    0.41
     dur
    0.40
     створення
    0.40
     somm
    0.40
    omme
    0.40
    POSITIVE LOGITS
    धि
    0.45
     brill
    0.43
     ':
    0.42
     sacrific
    0.42
     trig
    0.41
     agitated
    0.39
     previewBuilder
    0.39
    澫
    0.39
    ވި
    0.38
     spaceShip
    0.38
    Act Density 14.095%

    No Known Activations