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

    Neuronpedia

    INDEX
    Explanations

    four seasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carried
    0.80
     Shining
    0.78
    вий
    0.76
     Hàn
    0.76
    лай
    0.76
     rip
    0.73
     রো
    0.72
     ní
    0.72
     Token
    0.71
    াজে
    0.71
    POSITIVE LOGITS
    ⃣
    1.35
    ️⃣
    1.30
    th
    1.25
    десят
    1.24
    teen
    1.22
    деся
    1.14
    hmC
    1.11
    ۣ
    1.10
    つの
    1.05
    ಿಯು
    1.02
    Act Density 0.476%

    No Known Activations