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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Eastern
    0.68
     Eastern
    0.64
    interval
    0.63
     Восто
    0.61
    ftone
    0.61
     Interval
    0.59
    eastern
    0.58
     interval
    0.57
     ticket
    0.56
     wherein
    0.55
    POSITIVE LOGITS
     வள்ளி
    0.78
    ilish
    0.75
     vyd
    0.74
     Sath
    0.72
    昊
    0.71
     enforcement
    0.71
     행
    0.69
     ইচ্ছ
    0.69
    二十
    0.68
    ygons
    0.66
    Act Density 0.056%

    No Known Activations