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

    Neuronpedia

    INDEX
    Explanations

    compound exercises

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     داستان
    0.63
    輕
    0.63
     repetitions
    0.61
     repetition
    0.59
    teborg
    0.58
    ឡើង
    0.57
     ре
    0.57
    ポジ
    0.57
    orms
    0.56
     lifts
    0.56
    POSITIVE LOGITS
     workday
    0.78
     جیل
    0.73
    ந்தோ
    0.70
     रॉबर्ट
    0.70
     chiesa
    0.70
     বিমানবন্দ
    0.69
     envió
    0.69
     locus
    0.69
     raíz
    0.68
    關注
    0.67
    Act Density 0.052%

    No Known Activations