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

    Neuronpedia

    INDEX
    Explanations

    prepositions and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ι
    0.46
    ابعة
    0.40
    트
    0.39
    オ
    0.38
    ن
    0.38
    લ્ડ
    0.38
    은
    0.38
     açúcar
    0.37
    ラ
    0.37
    라스
    0.36
    POSITIVE LOGITS
    0.37
    ه‌
    0.36
     dette
    0.35
     This
    0.35
     The
    0.34
    v
    0.34
    nect
    0.33
    ush
    0.33
    ining
    0.33
    you
    0.33
    Act Density 0.127%

    No Known Activations