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

    Neuronpedia

    INDEX
    Explanations

    surgery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tomb
    -0.08
     sayılı
    -0.07
    ᶏ
    -0.07
    桁
    -0.07
    用人单位
    -0.07
    :event
    -0.07
    Wars
    -0.07
    Wa
    -0.07
     Visibility
    -0.07
    檩
    -0.06
    POSITIVE LOGITS
     dl
    0.08
     NSDate
    0.07
     optimizing
    0.07
     Contributor
    0.07
    Profile
    0.07
    訓練
    0.06
    Translator
    0.06
     melt
    0.06
     العلاقات
    0.06
    	actual
    0.06
    Act Density 0.011%

    No Known Activations