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
     urgent
    -0.07
    	wc
    -0.07
     pirates
    -0.06
     staffing
    -0.06
    ايل
    -0.06
    qli
    -0.06
    ATO
    -0.06
     loạt
    -0.06
    問題
    -0.06
    -def
    -0.06
    POSITIVE LOGITS
    ीड
    0.07
     Julien
    0.06
     devast
    0.06
     Bever
    0.06
     intrig
    0.06
     Quotes
    0.06
    .''↵↵
    0.06
    !");
    0.06
     соч
    0.06
     سبز
    0.06
    Act Density 0.083%

    No Known Activations