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

    Neuronpedia

    INDEX
    Explanations

    Now we're left with:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     then
    0.63
     eventually
    0.60
     still
    0.59
     आजही
    0.58
     thereupon
    0.57
    然后
    0.56
    Still
    0.56
     아직
    0.56
     vẫn
    0.55
     atunci
    0.52
    POSITIVE LOGITS
     Теперь
    0.81
     본격
    0.65
     теперь
    0.64
     тепер
    0.64
    Теперь
    0.64
    有了
    0.63
     oficialmente
    0.57
     artık
    0.56
     حالا
    0.54
     Now
    0.53
    Act Density 0.006%

    No Known Activations