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

    Neuronpedia

    INDEX
    Explanations

    closer to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ၜ
    0.44
     anb
    0.41
    MathMarks
    0.39
    ኘት
    0.39
    いが
    0.39
    ้อง
    0.38
     dụ
    0.38
    EMBER
    0.38
    ولوج
    0.37
    מין
    0.37
    POSITIVE LOGITS
     took
    0.42
     multiprocessing
    0.41
     caught
    0.39
     scrapped
    0.39
     নাও
    0.39
     multitasking
    0.38
     displays
    0.38
     skipped
    0.38
    жнее
    0.38
    displays
    0.37
    Act Density 0.001%

    No Known Activations