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

    Neuronpedia

    INDEX
    Explanations

    URLs for organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сім
    0.39
    魅力
    0.38
    гру
    0.36
    zv
    0.36
     Parry
    0.35
     वही
    0.34
     SVC
    0.34
    qu
    0.33
    truth
    0.33
     правда
    0.33
    POSITIVE LOGITS
     گذ
    0.43
     Yr
    0.42
     Kyl
    0.40
     osob
    0.39
     smok
    0.38
     乀
    0.38
    ษ
    0.38
     McGu
    0.38
     fy
    0.37
     proceder
    0.37
    Act Density 0.005%

    No Known Activations