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

    Neuronpedia

    INDEX
    Explanations

    Ring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     معين
    0.42
    ogical
    0.42
    ͌
    0.40
     ث
    0.39
     soy
    0.38
    ára
    0.38
    ONTAL
    0.38
     شرا
    0.38
     bort
    0.38
     لو
    0.38
    POSITIVE LOGITS
    Ring
    1.23
     Ring
    1.20
     ring
    1.16
     RING
    1.05
     Rings
    0.98
     rings
    0.96
    环
    0.92
     रिंग
    0.90
    ring
    0.89
     anillos
    0.89
    Act Density 0.007%

    No Known Activations