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

    Neuronpedia

    INDEX
    Explanations

    specialized language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inmediatamente
    0.44
     IMMEDI
    0.43
    Immediately
    0.42
     immediatamente
    0.39
     immediately
    0.39
     odmah
    0.39
     sofort
    0.38
    immediately
    0.38
    atthe
    0.38
     imediatamente
    0.38
    POSITIVE LOGITS
     zde
    0.46
     Verbesser
    0.44
     Soft
    0.41
     Phaser
    0.40
     Tile
    0.39
     Riders
    0.39
     物
    0.38
     Programm
    0.38
     soft
    0.38
     Chemistry
    0.38
    Act Density 0.000%

    No Known Activations