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

    Neuronpedia

    INDEX
    Explanations

    determine if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    How
    1.18
     How
    1.04
     معنى
    1.03
     كيفية
    0.99
    how
    0.96
     어떻게
    0.93
     कैसे
    0.92
     bagaimana
    0.91
    是怎么
    0.91
    tfrac
    0.90
    POSITIVE LOGITS
     which
    0.83
     if
    0.77
     accelerated
    0.69
     confident
    0.63
     precise
    0.62
     specializing
    0.61
     focused
    0.61
     whether
    0.60
     whose
    0.60
     editing
    0.59
    Act Density 0.284%

    No Known Activations