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

    Neuronpedia

    INDEX
    Explanations

    product series names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ใน
    1.41
    이라는
    1.33
    기
    1.32
    트에
    1.30
    ната
    1.24
    이지만
    1.24
    자
    1.21
    夥伴
    1.20
    ة
    1.20
    ן
    1.19
    POSITIVE LOGITS
     boardroom
    1.17
     ammonia
    1.16
    })
    1.14
     bearer
    1.11
     kicker
    1.11
     foothills
    1.10
     warehousing
    1.10
     linestyle
    1.08
     shackles
    1.07
     berichtet
    1.05
    Act Density 0.002%

    No Known Activations