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

    Neuronpedia

    INDEX
    Explanations

    as follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    1.03
    các
    1.02
    ний
    1.02
    ت
    0.98
    ния
    0.95
    ровать
    0.95
     জন্য
    0.94
    تر
    0.93
    нюю
    0.92
    ર્સ
    0.90
    POSITIVE LOGITS
     follows
    2.60
     opposed
    2.16
    follows
    2.00
     though
    1.88
     well
    1.82
    ymmet
    1.81
     part
    1.62
    cribing
    1.60
     soon
    1.58
     будто
    1.55
    Act Density 0.162%

    No Known Activations