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

    Neuronpedia

    INDEX
    Explanations

    explosion of X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ку
    0.54
    hran
    0.53
    谀
    0.52
    leaning
    0.50
     आराम
    0.49
    handedly
    0.49
    herent
    0.48
    argu
    0.47
    рай
    0.46
     लगातार
    0.45
    POSITIVE LOGITS
     explosion
    1.46
     explos
    1.41
     explosive
    1.41
     explodes
    1.40
     explosions
    1.39
     explode
    1.38
    爆炸
    1.25
     exploding
    1.23
    爆
    1.19
     exploded
    1.16
    Act Density 0.097%

    No Known Activations