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

    Neuronpedia

    INDEX
    Explanations

    analyze, analysing, analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lL
    1.04
    िफिशियल
    1.00
    átiles
    0.96
     anteced
    0.94
    től
    0.93
    ₤
    0.93
    lighter
    0.92
     subscript
    0.92
    листы
    0.92
     сахар
    0.91
    POSITIVE LOGITS
    mathop
    1.02
     того
    1.01
    <0x0D>
    0.98
     fist
    0.96
    ी
    0.94
     टीचिंग
    0.90
    可知
    0.89
     covariance
    0.89
    তথ্য
    0.89
    ਣ
    0.84
    Act Density 0.317%

    No Known Activations