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

    Neuronpedia

    INDEX
    Explanations

    start of contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ihren
    0.72
    ཋ
    0.70
    Ꭽ
    0.70
     wyłącznie
    0.69
     séptimo
    0.69
    🔟
    0.69
    Aqui
    0.68
     descrizione
    0.68
     этим
    0.67
     essas
    0.67
    POSITIVE LOGITS
     and
    1.18
     the
    1.06
    ال
    0.94
     that
    0.80
     an
    0.79
     a
    0.79
     to
    0.76
     at
    0.73
     or
    0.71
    2
    0.71
    Act Density 0.101%

    No Known Activations