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

    Neuronpedia

    INDEX
    Explanations

    interactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    artists
    -0.07
     naš
    -0.06
    魔法
    -0.06
    وي
    -0.06
    рок
    -0.06
     *****
    -0.06
    Processed
    -0.06
     požadav
    -0.06
    Exit
    -0.06
    ldkf
    -0.06
    POSITIVE LOGITS
     WTF
    0.07
     citiz
    0.07
    }\\
    0.06
       ↵    ↵
    0.06
     Patterson
    0.06
     sdf
    0.06
     gid
    0.06
     člen
    0.06
     gum
    0.06
    ==$
    0.06
    Act Density 0.127%

    No Known Activations