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

    Neuronpedia

    INDEX
    Explanations

    here today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     despatch
    0.46
     rumours
    0.45
    有望
    0.45
     tilts
    0.45
     deberían
    0.44
     favoured
    0.43
     perox
    0.43
     Bên
    0.42
     wären
    0.42
     ماسکو
    0.41
    POSITIVE LOGITS
    创作
    0.47
    ontal
    0.43
    英寸
    0.42
    开始
    0.42
     δια
    0.41
    Wheel
    0.40
     开始
    0.40
    器的
    0.39
    astă
    0.39
    过程中
    0.38
    Act Density 0.002%

    No Known Activations