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

    Neuronpedia

    INDEX
    Explanations

    @Transactional annotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ח
    1.75
    ্ক
    1.48
    েন
    1.48
     saiu
    1.48
    1.41
    Боль
    1.40
    odies
    1.39
    ین
    1.39
     uscita
    1.39
     टुडे
    1.35
    POSITIVE LOGITS
     вино
    2.05
    ture
    2.00
    t
    1.97
     boulder
    1.85
    tR
    1.75
    ez
    1.72
    orado
    1.66
     fluttering
    1.65
    rocities
    1.64
    tung
    1.64
    Act Density 0.001%

    No Known Activations