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

    Neuronpedia

    INDEX
    Explanations

    magical artifacts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eryl
    -0.07
    rive
    -0.06
    imshow
    -0.06
     occupations
    -0.06
    .scatter
    -0.06
    pickup
    -0.06
    emie
    -0.06
     Justice
    -0.06
     minimized
    -0.06
     결혼
    -0.06
    POSITIVE LOGITS
     DK
    0.07
    umer
    0.07
     Komment
    0.07
     حق
    0.06
     nije
    0.06
    (CL
    0.06
     Commentary
    0.06
    .buttons
    0.06
    .MM
    0.06
     Diablo
    0.06
    Act Density 0.054%

    No Known Activations