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

    Neuronpedia

    INDEX
    Explanations

    Spanish punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reni
    0.62
    ことが
    0.60
     పేర్కొ
    0.60
    кова
    0.58
    monary
    0.58
     ventral
    0.58
     альтерна
    0.58
    kov
    0.58
     ショルダーバッグ
    0.56
     విష
    0.56
    POSITIVE LOGITS
     soy
    1.14
     qué
    1.08
     Saber
    1.02
     Soy
    1.00
     Qué
    1.00
     Estoy
    0.98
     Tengo
    0.97
     وانا
    0.97
     vos
    0.96
     estoy
    0.95
    Act Density 0.110%

    No Known Activations