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
     Á
    -0.07
     Panel
    -0.07
     商品
    -0.07
     arguments
    -0.07
     Abs
    -0.07
    eyen
    -0.07
     overridden
    -0.06
     Susp
    -0.06
    False
    -0.06
     Schl
    -0.06
    POSITIVE LOGITS
     woke
    0.07
    outfile
    0.07
     Γου
    0.07
    (dd
    0.07
    .Listen
    0.06
     شه
    0.06
    stderr
    0.06
    (Type
    0.06
    ={↵
    0.06
    =edge
    0.06
    Act Density 0.002%

    No Known Activations