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

    Neuronpedia

    INDEX
    Explanations

    is/are/be + state change verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viewed
    0.30
    hed
    0.27
     reimag
    0.27
     interpreted
    0.27
     diskut
    0.27
     treated
    0.25
    ives
    0.24
     hed
    0.24
     discours
    0.24
     presented
    0.24
    POSITIVE LOGITS
    LOLL
    0.23
    確
    0.22
     आरओ
    0.21
    ाइए
    0.20
    тт
    0.20
    驄
    0.20
     creado
    0.20
    AddModel
    0.20
    বর্তী
    0.20
    鱷
    0.20
    Act Density 0.024%

    No Known Activations