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

    Neuronpedia

    INDEX
    Explanations

    "i can" in various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হন
    0.82
    CreateCharacter
    0.81
     करें
    0.80
     کنید
    0.77
    änk
    0.75
     warns
    0.73
     넣
    0.73
    ceti
    0.73
    CrossOrigin
    0.73
     کریں
    0.72
    POSITIVE LOGITS
     tôi
    1.72
    私は
    1.55
     я
    1.55
     мне
    1.54
    我现在
    1.54
     मुझे
    1.51
     tengo
    1.49
     saya
    1.48
    我
    1.48
     mogę
    1.47
    Act Density 0.121%

    No Known Activations