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

    Neuronpedia

    INDEX
    Explanations

    by making

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     είναι
    0.49
     إذا
    0.49
     ከሆነ
    0.49
     اگر
    0.46
     якщо
    0.46
    來看
    0.46
     faudra
    0.46
     തുട
    0.45
     असल्यास
    0.45
     איך
    0.45
    POSITIVE LOGITS
     thereby
    0.74
     ensures
    0.56
    同时也
    0.54
     ensuring
    0.51
     Thereby
    0.51
    从而
    0.50
     reduces
    0.48
    함으로써
    0.45
     maximizes
    0.44
     simultaneously
    0.44
    Act Density 0.023%

    No Known Activations