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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jj
    -0.07
     rv
    -0.07
    isLoggedIn
    -0.07
     ㅡ
    -0.07
     aren
    -0.06
    videos
    -0.06
     retire
    -0.06
     quat
    -0.06
    Link
    -0.06
     squ
    -0.06
    POSITIVE LOGITS
     breakthrough
    0.06
     قدر
    0.06
     Nietzsche
    0.06
    すると
    0.06
     Epidemi
    0.06
    IMO
    0.06
    落ち
    0.06
    大全
    0.06
    ermal
    0.06
     почему
    0.06
    Act Density 0.061%

    No Known Activations