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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pony
    -0.07
     hut
    -0.07
     충
    -0.07
    amera
    -0.06
    佐
    -0.06
     relegated
    -0.06
    (inertia
    -0.06
     пол
    -0.06
    řich
    -0.06
    EXPECT
    -0.06
    POSITIVE LOGITS
     masterpiece
    0.06
    Youtube
    0.06
    -consuming
    0.06
    Cam
    0.06
    _tb
    0.06
    */↵↵↵
    0.06
    _FAR
    0.06
    683
    0.06
     usefulness
    0.06
    �
    0.06
    Act Density 0.013%

    No Known Activations