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

    Neuronpedia

    INDEX
    Explanations

    only ... can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     encarg
    0.47
    ंश
    0.43
    ovou
    0.43
     ছাড়াই
    0.43
     regards
    0.40
    mutable
    0.39
     invece
    0.39
    ളി
    0.38
    ഭം
    0.38
    ancial
    0.38
    POSITIVE LOGITS
     Только
    0.62
     Only
    0.57
    才能
    0.53
     तभी
    0.52
    才可以
    0.51
    只有
    0.51
     тільки
    0.51
    Only
    0.49
    可通过
    0.48
     mới
    0.48
    Act Density 0.028%

    No Known Activations