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

    Neuronpedia

    INDEX
    Explanations

    here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    સર
    0.88
    ктор
    0.87
    ما
    0.86
    Após
    0.86
    ق
    0.85
    ୍କ
    0.84
    extrémité
    0.82
    ätzen
    0.82
    ्स
    0.81
     propriétés
    0.81
    POSITIVE LOGITS
     l
    1.02
    l
    0.94
     U
    0.94
     N
    0.93
     n
    0.88
     M
    0.83
    U
    0.82
    geld
    0.81
     sini
    0.80
     നിന്ന്
    0.80
    Act Density 0.129%

    No Known Activations