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

    Neuronpedia

    INDEX
    Explanations

    listen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dương
    -0.07
    SetValue
    -0.07
     Huffman
    -0.07
    Codigo
    -0.07
     VR
    -0.06
    .subplots
    -0.06
    xz
    -0.06
     개발
    -0.06
    eparator
    -0.06
    war
    -0.06
    POSITIVE LOGITS
    READING
    0.07
     обязан
    0.07
     dick
    0.06
     ISSN
    0.06
    esinin
    0.06
    шись
    0.06
    _CAMERA
    0.06
     efficiencies
    0.06
    ,↵↵↵↵
    0.06
    白
    0.06
    Act Density 0.003%

    No Known Activations