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

    Neuronpedia

    INDEX
    Explanations

    ">

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    в
    2.07
    nić
    2.00
    інки
    1.96
    нига
    1.95
     điển
    1.94
    𝙞
    1.94
     hwnd
    1.85
     wors
    1.82
     denn
    1.81
     wisata
    1.81
    POSITIVE LOGITS
    al
    2.28
    am
    1.91
    e
    1.67
    ar
    1.64
    an
    1.64
    آ
    1.62
     carb
    1.62
    গ্রস্থ
    1.59
     welded
    1.57
    лили
    1.56
    Act Density 0.001%

    No Known Activations