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

    Neuronpedia

    INDEX
    Explanations

    systems or programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    бири
    0.71
    etti
    0.70
     midst
    0.70
    लय
    0.68
     ymp
    0.68
    blade
    0.68
    imizi
    0.68
    eep
    0.67
     같습니다
    0.66
    iv
    0.66
    POSITIVE LOGITS
     miracles
    0.87
     miracle
    0.83
     Wonder
    0.83
     wonder
    0.82
    ers
    0.82
     wonders
    0.81
     वाली
    0.81
     environments
    0.78
     innovations
    0.78
     monarch
    0.78
    Act Density 1.566%

    No Known Activations