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

    Neuronpedia

    INDEX
    Explanations

    Japanese and Korean common particles and sentence connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     및
    1.49
    및
    1.25
     کے
    1.24
     కోసం
    1.15
    으로
    1.15
     және
    1.14
     uchun
    1.08
    이며
    1.06
     និង
    1.06
    を選択
    1.06
    POSITIVE LOGITS
     단순히
    0.86
    自分の
    0.81
    自分が
    0.66
    どんな
    0.65
    どのような
    0.64
     اپنے
    0.60
    それは
    0.60
    それを
    0.59
    自己
    0.59
    今
    0.58
    Act Density 0.031%

    No Known Activations