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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ((↵
    -0.07
     ")↵
    -0.06
    lerle
    -0.06
     ();↵↵
    -0.06
    ิ
    -0.06
     méth
    -0.06
    /original
    -0.06
    ']]]↵
    -0.06
    );\↵
    -0.06
    indered
    -0.06
    POSITIVE LOGITS
    ้อน
    0.07
     eas
    0.07
     DWC
    0.06
     watching
    0.06
    composer
    0.06
    .FromResult
    0.06
    ясь
    0.06
     adjustable
    0.06
    اى
    0.06
    ج
    0.06
    Act Density 0.000%

    No Known Activations