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

    Neuronpedia

    INDEX
    Explanations

    y apunta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ने
    1.09
    الح
    1.09
     bords
    1.04
     ώστε
    1.02
    الت
    1.00
    。
    1.00
     electrónicos
    0.99
     сих
    0.95
    ת
    0.95
    قل
    0.92
    POSITIVE LOGITS
    or
    1.16
    ين
    1.02
    ंगाबाद
    1.02
    ায়
    1.01
    ppure
    0.95
    ou
    0.95
     unstoppable
    0.93
    re
    0.92
    l
    0.88
    GoObject
    0.87
    Act Density 0.468%

    No Known Activations