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

    Neuronpedia

    INDEX
    Explanations

    strategies and improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Když
    0.56
     మీరు
    0.55
     bạn
    0.54
     লোকেরা
    0.52
     وقتی
    0.52
    Когда
    0.51
     eğer
    0.50
     когда
    0.50
     dacă
    0.50
     যদি
    0.49
    POSITIVE LOGITS
    including
    0.77
     and
    0.72
     including
    0.72
    and
    0.63
     மற்றும்
    0.62
     включая
    0.61
    および
    0.60
    、
    0.60
    และ
    0.59
    包括
    0.59
    Act Density 0.138%

    No Known Activations