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

    Neuronpedia

    INDEX
    Explanations

    you are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nécess
    0.38
     நாம்
    0.37
    요
    0.36
     առաջ
    0.36
     করছে
    0.35
     assimilation
    0.35
     інших
    0.35
    Пер
    0.35
     ہوگی
    0.35
     quelconque
    0.35
    POSITIVE LOGITS
     are
    0.53
     can
    0.51
     guys
    0.50
     yourself
    0.49
    ths
    0.48
     want
    0.46
     have
    0.46
     didn
    0.45
     cannot
    0.45
    uu
    0.44
    Act Density 0.044%

    No Known Activations