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

    Neuronpedia

    INDEX
    Explanations

    rapid language expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ContextHeader
    0.42
     জোগ
    0.42
     ChAT
    0.39
    秵
    0.39
     padassa
    0.38
    ლებელია
    0.38
     chargingStation
    0.37
     版
    0.37
    ":"","
    0.37
     動画
    0.37
    POSITIVE LOGITS
     your
    0.55
     Your
    0.55
    Your
    0.55
    your
    0.45
    odi
    0.43
     Sher
    0.42
     Baby
    0.42
     ඔබේ
    0.42
     lavish
    0.40
     Scrap
    0.40
    Act Density 0.000%

    No Known Activations