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

    Neuronpedia

    INDEX
    Explanations

    some of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     যেদিন
    0.41
    ніше
    0.40
     jiné
    0.40
    merich
    0.40
     Brookfield
    0.40
     관계
    0.39
    BURTS
    0.39
    രാഷ്ട്ര
    0.38
    nem
    0.38
    ತೆಗೆ
    0.38
    POSITIVE LOGITS
    amon
    0.49
    Bot
    0.46
    ain
    0.45
     клави
    0.44
     deceler
    0.43
     interpolation
    0.42
     Assembly
    0.42
     추
    0.42
     "),
    0.42
     Haziran
    0.41
    Act Density 8.954%

    No Known Activations