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

    Neuronpedia

    INDEX
    Explanations

    crash, collision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    教学
    0.42
    胁
    0.40
     dries
    0.36
    ഥ
    0.36
    ля
    0.35
    ଃ
    0.35
    kmale
    0.35
     அறிக
    0.35
    িলিয়া
    0.35
     رئيس
    0.34
    POSITIVE LOGITS
     Crash
    0.52
     crash
    0.48
     Collision
    0.41
    ција
    0.41
    Crash
    0.41
    crash
    0.39
     collision
    0.37
     Editable
    0.37
    ບັນ
    0.37
     crashed
    0.36
    Act Density 0.016%

    No Known Activations