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

    Neuronpedia

    INDEX
    Explanations

    control, controlled, victim, breaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     requ
    0.48
     blades
    0.43
     heavy
    0.42
     dyspe
    0.40
     throughput
    0.40
     تحقيق
    0.39
     sportsmen
    0.39
    の日
    0.39
     nuit
    0.38
     fibers
    0.38
    POSITIVE LOGITS
    伟大
    0.49
    ت
    0.46
    িশীল
    0.46
    at
    0.44
    ก่
    0.43
     Izv
    0.42
    Đây
    0.42
    nows
    0.42
    所以
    0.41
    תה
    0.41
    Act Density 0.003%

    No Known Activations