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

    Neuronpedia

    INDEX
    Explanations

    ranking is hard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ስቃ
    0.47
    udarstven
    0.45
    觎
    0.45
    МИ
    0.43
    配信
    0.43
    Bien
    0.42
    ])*
    0.42
    Sicilian
    0.42
    INavigation
    0.42
     ವಿಧಾನ
    0.41
    POSITIVE LOGITS
     work
    0.54
     you
    0.52
     usamos
    0.51
     você
    0.50
     drinkers
    0.48
     Work
    0.47
     expands
    0.45
     jūs
    0.45
     use
    0.45
     water
    0.45
    Act Density 0.010%

    No Known Activations