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

    Neuronpedia

    INDEX
    Explanations

    Web page content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    엘
    -0.07
    溫
    -0.06
     Hra
    -0.06
    -five
    -0.06
    籍
    -0.06
     konu
    -0.06
     значение
    -0.06
    _XML
    -0.06
     Represents
    -0.06
    .UPDATE
    -0.06
    POSITIVE LOGITS
     refrigerator
    0.06
    (process
    0.06
    ogram
    0.06
    acks
    0.06
     apartments
    0.06
    esis
    0.06
    \Events
    0.06
     mono
    0.06
     Easily
    0.06
    arsimp
    0.06
    Act Density 0.007%

    No Known Activations