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

    Neuronpedia

    INDEX
    Explanations

    Google Drive links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ($("#
    -0.08
    �
    -0.07
    Scheme
    -0.07
    .ComboBoxStyle
    -0.07
     Provides
    -0.07
     MIX
    -0.07
    ῾
    -0.07
    ▴
    -0.07
    ﭭ
    -0.06
    微微
    -0.06
    POSITIVE LOGITS
     Chronicles
    0.07
     players
    0.07
    খ
    0.07
    礼拜
    0.07
    August
    0.07
    结婚
    0.07
     TR
    0.06
    antal
    0.06
    啊
    0.06
    快手
    0.06
    Act Density 0.003%

    No Known Activations