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

    Neuronpedia

    INDEX
    Explanations

    mysterious differences lever revenge CX

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     satire
    0.49
     لي
    0.45
     اخبار
    0.43
    ième
    0.42
    Gmail
    0.42
     دون
    0.42
     المر
    0.42
    ◀
    0.42
     Procurement
    0.41
     Gmail
    0.40
    POSITIVE LOGITS
     čo
    0.49
     üçün
    0.48
     unwitting
    0.48
    İZ
    0.47
    手が
    0.45
     Heel
    0.45
    槨
    0.44
    čio
    0.44
     MCS
    0.43
    就
    0.43
    Act Density 0.000%

    No Known Activations