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

    Neuronpedia

    INDEX
    Explanations

    24/7 helplines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    因子
    0.46
     MERCHANT
    0.45
    Merchant
    0.41
    ிலான
    0.39
    Dm
    0.39
     boxShadow
    0.39
    MASTER
    0.38
    िसिटी
    0.38
    merchant
    0.38
    指数
    0.38
    POSITIVE LOGITS
    遜
    0.43
    ))
    0.43
     няма
    0.43
    étera
    0.41
     siap
    0.41
    ාල
    0.40
    ’
    0.40
     bás
    0.40
    決して
    0.40
    க
    0.40
    Act Density 0.003%

    No Known Activations