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

    Neuronpedia

    INDEX
    Explanations

    discussing vite migration and approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (!
    1.78
    ’
    1.70
    '
    1.65
     historians
    1.48
    erns
    1.38
    inerary
    1.38
     whilst
    1.36
     with
    1.32
    '!
    1.32
     while
    1.31
    POSITIVE LOGITS
     сути
    2.07
     lugar
    2.04
     ayrı
    2.03
     immédiatement
    2.02
    kyo
    2.00
    ھر
    1.99
     emerg
    1.98
    صبح
    1.97
    ຖານ
    1.95
     lieu
    1.94
    Act Density 0.411%

    No Known Activations