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

    Neuronpedia

    INDEX
    Explanations

    file path renaming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ล
    0.48
     data
    0.47
    JSON
    0.46
     людей
    0.45
    ！！！！
    0.45
    วิว
    0.44
    ﺪ
    0.44
     સાથે
    0.43
     JSON
    0.43
    มาก
    0.43
    POSITIVE LOGITS
     preclude
    0.43
     precluded
    0.43
    😧
    0.43
     invariably
    0.42
    cedent
    0.42
     unprofitable
    0.41
     unduly
    0.41
     स्कूटर
    0.41
    욀
    0.41
    cnica
    0.41
    Act Density 0.003%

    No Known Activations