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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Whereas
    -0.07
     Employer
    -0.07
     Glas
    -0.06
     ed
    -0.06
     scatter
    -0.06
     gam
    -0.06
     bizim
    -0.06
     find
    -0.06
     guilty
    -0.06
     crawling
    -0.06
    POSITIVE LOGITS
    北市
    0.07
    _candidate
    0.07
    invoices
    0.06
     wxDefault
    0.06
     трохи
    0.06
    �
    0.06
    ＿＿＿＿＿＿＿＿
    0.06
    \system
    0.06
     svou
    0.06
    	pw
    0.06
    Act Density 0.008%

    No Known Activations