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

    Neuronpedia

    INDEX
    Explanations

    collision detection, impact, crash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Coll
    0.49
     кола
    0.49
    Coll
    0.48
     कोल
    0.47
     Collagen
    0.47
     콜
    0.47
     colloid
    0.46
     collars
    0.45
     collar
    0.44
     컬
    0.44
    POSITIVE LOGITS
    Bots
    0.68
     bots
    0.65
     Bots
    0.61
    bots
    0.58
     συγκ
    0.58
    Сто
    0.57
     충
    0.57
    突
    0.52
     стол
    0.50
    충
    0.50
    Act Density 0.004%

    No Known Activations