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

    Neuronpedia

    INDEX
    Explanations

    categories or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    1.20
    нг
    1.16
    eous
    1.12
    тся
    1.09
    iya
    1.07
    us
    1.06
    लिक
    1.02
     высо
    1.02
    ください
    1.00
    ੀ
    0.99
    POSITIVE LOGITS
    그래서
    0.95
    ATION
    0.94
    す
    0.93
    (
    0.89
    (_,
    0.89
    Enable
    0.87
    علم
    0.87
     allerdings
    0.85
    如果在
    0.85
    CREATE
    0.84
    Act Density 0.000%

    No Known Activations