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

    Neuronpedia

    INDEX
    Explanations

    using, via, through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Used
    0.85
    }{*}{}
    0.77
     USED
    0.76
     Used
    0.74
    седнев
    0.73
     hyvä
    0.72
    <unused1054>
    0.71
    どころ
    0.71
    embangkan
    0.71
    USED
    0.71
    POSITIVE LOGITS
     using
    4.76
     via
    4.18
    using
    4.14
     Using
    3.99
     باستخدام
    3.79
     usando
    3.79
     menggunakan
    3.78
    Using
    3.76
     utilizando
    3.66
     utilizzando
    3.57
    Act Density 1.298%

    No Known Activations