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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ieux
    -0.08
    Porn
    -0.06
     newborn
    -0.06
     lush
    -0.06
     focused
    -0.06
     summary
    -0.06
    	nodes
    -0.06
    ovali
    -0.06
     Europe
    -0.06
    情况
    -0.06
    POSITIVE LOGITS
    .email
    0.07
    :[],↵
    0.06
    .Excel
    0.06
    TextLabel
    0.06
    -relative
    0.06
     absol
    0.06
    ські
    0.06
    .WebDriver
    0.06
     "'",
    0.06
     Phonetic
    0.06
    Act Density 0.006%

    No Known Activations