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

    Neuronpedia

    INDEX
    Explanations

    of these

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jednym
    0.36
     所有
    0.32
     banheiro
    0.30
    leq
    0.30
    ボリー
    0.30
     générale
    0.29
    id
    0.29
    0
    0.29
    龰
    0.29
     meisten
    0.29
    POSITIVE LOGITS
    ных
    0.48
     the
    0.47
    ные
    0.45
    The
    0.43
     this
    0.41
     these
    0.40
    의
    0.38
    ના
    0.37
    -
    0.37
    ي
    0.37
    Act Density 0.031%

    No Known Activations