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

    Neuronpedia

    INDEX
    Explanations

    addresses and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ইংরেজি
    0.70
    োসিয়ে
    0.67
    Ờ
    0.65
    巧
    0.64
    ជាប់
    0.63
     одно
    0.63
    Satisf
    0.62
    లలో
    0.62
     अंग्रेजों
    0.62
     Subdistrict
    0.60
    POSITIVE LOGITS
     Farn
    0.96
     Hove
    0.96
     Harrow
    0.95
     Burgess
    0.94
     Kew
    0.92
     Brack
    0.90
     Barnes
    0.90
     Tun
    0.89
     Ching
    0.89
     Finch
    0.88
    Act Density 0.296%

    No Known Activations