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

    Neuronpedia

    INDEX
    Explanations

    causes and effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Was
    0.90
     Was
    0.82
     Were
    0.75
    Were
    0.73
     были
    0.73
     був
    0.72
     असतो
    0.71
     gewesen
    0.70
     WAS
    0.69
    WAS
    0.69
    POSITIVE LOGITS
     helped
    2.10
     led
    1.94
     resulted
    1.93
     spurred
    1.86
     sparked
    1.86
     contributed
    1.84
     prompted
    1.81
     spawned
    1.71
     allowed
    1.69
     enabled
    1.65
    Act Density 0.244%

    No Known Activations