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

    Neuronpedia

    INDEX
    Explanations

    breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.20
    ي
    1.13
    de
    1.06
    க
    1.02
    in
    0.99
    ש
    0.98
    یز
    0.97
    К
    0.95
    ק
    0.95
    et
    0.94
    POSITIVE LOGITS
     וכ
    0.98
     borderRadius
    0.90
    Interpol
    0.88
    はこの
    0.87
     منظور
    0.87
     διάρκ
    0.85
    是指
    0.84
     그래도
    0.84
    IL
    0.83
    ွဲ
    0.82
    Act Density 0.000%

    No Known Activations