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

    Neuronpedia

    INDEX
    Explanations

    explosions and explosive force

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     архитек
    0.41
    Abraham
    0.41
     Abraham
    0.39
    Steady
    0.39
     Hải
    0.39
    ချုပ်
    0.39
    Hall
    0.38
    ₁(
    0.38
     continueRoutine
    0.38
     याता
    0.38
    POSITIVE LOGITS
     explosion
    1.94
     explosive
    1.91
     explosions
    1.91
     explode
    1.89
     explodes
    1.78
     exploding
    1.76
     explos
    1.73
     exploded
    1.72
    爆炸
    1.69
    爆
    1.63
    Act Density 0.015%

    No Known Activations