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

    Neuronpedia

    INDEX
    Explanations

    multilingual endings and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WI
    0.40
    emphas
    0.40
     ডাকে
    0.39
     erwähnt
    0.39
    ages
    0.38
     पिछ
    0.38
     আহসান
    0.37
    猚
    0.37
    䋆
    0.37
    WI
    0.37
    POSITIVE LOGITS
    거나
    0.41
    diri
    0.41
    miştir
    0.40
    셈
    0.40
     basta
    0.39
    시다
    0.38
    veriş
    0.38
    sud
    0.38
     cas
    0.37
     cashew
    0.37
    Act Density 0.000%

    No Known Activations