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

    Neuronpedia

    INDEX
    Explanations

    by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utilisant
    1.02
     use
    1.02
     используют
    1.00
     menggunakan
    0.99
     usar
    0.98
     использует
    0.97
    Use
    0.95
     Use
    0.93
    可以使用
    0.91
     χρήση
    0.91
    POSITIVE LOGITS
     by
    2.81
    by
    2.27
     By
    2.14
    By
    2.06
     indem
    2.05
     oleh
    1.91
     путем
    1.86
    ById
    1.60
    によって
    1.57
    bys
    1.52
    Act Density 0.339%

    No Known Activations