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

    Neuronpedia

    INDEX
    Explanations

    accidents, collisions, or negative events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অপেক্ষা
    0.75
    مع
    0.74
    賦
    0.70
    processed
    0.69
    HeaderAccept
    0.69
    βε
    0.68
    লিউ
    0.67
     поха
    0.66
     আচার
    0.66
     informativa
    0.66
    POSITIVE LOGITS
     collision
    1.94
     collided
    1.93
     crashed
    1.91
     collisions
    1.91
     knocked
    1.84
     accident
    1.83
     crashing
    1.83
     crash
    1.83
     colliding
    1.83
     crashes
    1.82
    Act Density 0.551%

    No Known Activations