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

    Neuronpedia

    INDEX
    Explanations

    perspectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    网站
    -0.08
    税
    -0.07
    All
    -0.07
    strap
    -0.07
     All
    -0.07
    PLUGIN
    -0.06
    Retrieve
    -0.06
     threshold
    -0.06
     Μπ
    -0.06
     all
    -0.06
    POSITIVE LOGITS
    名
    0.06
    *math
    0.06
    :model
    0.06
    NSNotificationCenter
    0.06
    	Text
    0.06
    cs
    0.06
    そんな
    0.06
     ча
    0.05
    ตาม
    0.05
     annotated
    0.05
    Act Density 0.093%

    No Known Activations