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

    Neuronpedia

    INDEX
    Explanations

    X-day itineraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seus
    0.31
     certaines
    0.30
     Arbeit
    0.30
     सारे
    0.30
     overridden
    0.29
     politiques
    0.28
     Killed
    0.28
     viele
    0.28
     Sabtu
    0.28
     Saya
    0.28
    POSITIVE LOGITS
     सदस्यीय
    0.41
     दिवसीय
    0.39
     sized
    0.33
     haired
    0.31
    dimensional
    0.31
    imensional
    0.30
     gallon
    0.30
     multi
    0.29
    }$-
    0.29
     dimensional
    0.29
    Act Density 0.122%

    No Known Activations