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

    Neuronpedia

    INDEX
    Explanations

    flex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aún
    -0.07
    city
    -0.06
    dark
    -0.06
     White
    -0.06
    еса
    -0.06
    áč
    -0.06
     qp
    -0.06
     superiority
    -0.06
    ičky
    -0.06
    ตรวจ
    -0.06
    POSITIVE LOGITS
     bergen
    0.07
    _matrices
    0.07
    (fil
    0.06
     uniforms
    0.06
     instantiated
    0.06
    ,h
    0.06
     purchases
    0.06
    utorials
    0.06
     typing
    0.06
     familia
    0.06
    Act Density 0.002%

    No Known Activations