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

    Neuronpedia

    INDEX
    Explanations

    comparative statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    你看
    0.95
    JFrame
    0.94
    machen
    0.91
    ීය
    0.89
     পরিত্র
    0.89
     solvation
    0.88
    🄴
    0.88
     heave
    0.88
    𝖎
    0.88
    ካከል
    0.87
    POSITIVE LOGITS
    g
    1.09
    il
    1.08
    on
    0.91
    an
    0.90
    ot
    0.88
    in
    0.85
    co
    0.84
    що
    0.83
    al
    0.82
    c
    0.81
    Act Density 0.004%

    No Known Activations