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

    Neuronpedia

    INDEX
    Explanations

    pole position, podium, victory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     racing
    0.50
     racers
    0.47
     racer
    0.44
     Turnier
    0.42
    Racing
    0.42
    缚
    0.42
    racing
    0.41
     helmet
    0.40
     Motorsport
    0.40
     Motorsports
    0.40
    POSITIVE LOGITS
     victory
    0.52
     pole
    0.50
     vitória
    0.49
     podium
    0.48
    Pole
    0.47
     Побе
    0.46
     wins
    0.46
     побе
    0.46
     poles
    0.43
    pole
    0.43
    Act Density 0.001%

    No Known Activations