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

    Neuronpedia

    INDEX
    Explanations

    programming questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Freedom
    -0.07
     enthusiast
    -0.07
     comed
    -0.07
     fashionable
    -0.07
     '>'
    -0.06
    82
    -0.06
     Lub
    -0.06
    %"↵
    -0.06
    ホテル
    -0.06
    Blocked
    -0.06
    POSITIVE LOGITS
     ilma
    0.07
     disgusted
    0.06
     nepří
    0.06
     اروپ
    0.06
    ceans
    0.06
     verst
    0.06
     derog
    0.06
     dovol
    0.06
     velice
    0.06
    Wow
    0.06
    Act Density 0.032%

    No Known Activations