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

    Neuronpedia

    INDEX
    Explanations

    Romance language articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在你
    0.85
     فيديو
    0.82
     USU
    0.81
     أخرى
    0.76
     Quite
    0.74
     documentation
    0.74
     rockets
    0.74
     frustration
    0.73
    立马
    0.73
     Comune
    0.72
    POSITIVE LOGITS
     la
    2.38
     las
    1.70
     los
    1.58
     την
    1.46
     les
    1.36
     το
    1.31
    La
    1.22
     La
    1.21
    la
    1.20
     gli
    1.17
    Act Density 0.175%

    No Known Activations