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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    afi
    -0.08
    ImagePath
    -0.07
    خانه
    -0.07
    ivated
    -0.06
    udence
    -0.06
     Digest
    -0.06
    (attrs
    -0.06
    wed
    -0.06
    amura
    -0.06
     Lena
    -0.06
    POSITIVE LOGITS
    香港
    0.07
    .Contact
    0.07
    .gui
    0.07
    แป
    0.07
     architectures
    0.07
    /');↵
    0.06
    (""))
    0.06
    っていた
    0.06
    \",↵
    0.06
    "],
    0.06
    Act Density 0.043%

    No Known Activations