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

    Neuronpedia

    INDEX
    Explanations

    i am / i'm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sufficient
    0.93
     equivalent
    0.92
     discernible
    0.89
     efficient
    0.84
    適切な
    0.83
     bárm
    0.82
    即可
    0.82
     permissible
    0.81
     निर्दिष्ट
    0.81
    いずれ
    0.80
    POSITIVE LOGITS
     wanna
    1.53
     хочу
    1.52
     want
    1.51
     wanting
    1.51
     quiero
    1.51
     alot
    1.49
     đang
    1.44
     tengo
    1.43
     tenho
    1.42
    อยาก
    1.42
    Act Density 0.330%

    No Known Activations