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

    Neuronpedia

    INDEX
    Explanations

    tensorflow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gardner
    -0.07
    肃
    -0.07
     ik
    -0.07
     plurality
    -0.07
    ize
    -0.07
     blur
    -0.06
     wholesale
    -0.06
    _CODE
    -0.06
    NX
    -0.06
     Garcia
    -0.06
    POSITIVE LOGITS
     tensorflow
    0.08
    nelle
    0.08
     มหาว
    0.07
     тебя
    0.07
    tensorflow
    0.07
     výsledky
    0.07
     tasarım
    0.07
     왜
    0.07
     ACLU
    0.07
     وحدة
    0.06
    Act Density 0.001%

    No Known Activations