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

    Neuronpedia

    INDEX
    Explanations

    late 2023/early 2024

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಾಗಲೇ
    0.39
    ຜ
    0.38
     kip
    0.37
    未来的
    0.37
    ফতরের
    0.37
     लिमिटेड
    0.36
    ่น
    0.35
     indicative
    0.35
    未来
    0.35
     futuras
    0.35
    POSITIVE LOGITS
    comers
    0.58
     late
    0.52
    comer
    0.52
    late
    0.48
     lat
    0.48
     lamented
    0.45
    lat
    0.45
     Lat
    0.44
    Lat
    0.44
     концов
    0.43
    Act Density 0.041%

    No Known Activations