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

    Neuronpedia

    INDEX
    Explanations

    only / single / one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     కొంత
    0.44
     magari
    0.40
    ியுடன்
    0.39
    一些
    0.38
    雰囲
    0.37
     sommige
    0.37
    सह
    0.37
     некоторые
    0.37
     casually
    0.36
    Casual
    0.36
    POSITIVE LOGITS
     only
    1.36
     только
    1.22
     ONLY
    1.18
    only
    1.17
    只有一个
    1.13
     Only
    1.11
    Only
    1.11
     chỉ
    1.09
     тільки
    1.09
     μόνο
    1.09
    Act Density 0.080%

    No Known Activations