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

    Neuronpedia

    INDEX
    Explanations

    sections about topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বেশকিছু
    0.30
     रखते
    0.29
    兘
    0.28
    whom
    0.27
    aw
    0.27
     besitzt
    0.27
     oftentimes
    0.27
     DIFFERENT
    0.27
    Все
    0.26
    紝
    0.26
    POSITIVE LOGITS
     privind
    0.48
     envolvendo
    0.47
     involving
    0.45
     tentang
    0.42
     on
    0.41
     about
    0.40
     مبنی
    0.39
    发生在
    0.39
     terhadap
    0.39
     regarding
    0.38
    Act Density 0.178%

    No Known Activations