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

    Neuronpedia

    INDEX
    Explanations

    spoke fluently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rugby
    0.42
     nồi
    0.40
     huyền
    0.40
     चौराहे
    0.39
     рублей
    0.39
     České
    0.38
     يمكنك
    0.38
     ফজ
    0.37
    乆
    0.37
    chandelier
    0.36
    POSITIVE LOGITS
     tertentu
    0.49
    有利于
    0.47
     memang
    0.46
    wego
    0.43
    有助于
    0.42
    an
    0.41
     geral
    0.41
    ță
    0.41
    a
    0.40
    ه
    0.40
    Act Density 0.000%

    No Known Activations