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

    Neuronpedia

    INDEX
    Explanations

    Code/configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _("
    -0.09
    ותו
    -0.08
    OPLE
    -0.08
    ન્�
    -0.08
    Z
    -0.08
     hypocr
    -0.08
    YNAM
    -0.08
    _(
    -0.08
    ukai
    -0.08
    այտ
    -0.07
    POSITIVE LOGITS
     swo
    0.09
     Del
    0.08
     Wow
    0.08
    宁
    0.07
    生产
    0.07
    飞
    0.07
     wow
    0.07
     garage
    0.07
    滨
    0.07
     Dealers
    0.07
    Act Density 0.001%

    No Known Activations