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

    Neuronpedia

    INDEX
    Explanations

    DS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     underscore
    -0.07
     информации
    -0.07
    оглас
    -0.07
    .npy
    -0.06
    .Marker
    -0.06
    oined
    -0.06
     영상
    -0.06
     =========================================================================
    -0.06
    Socket
    -0.06
    Runnable
    -0.06
    POSITIVE LOGITS
    Enterprise
    0.07
     Butler
    0.06
    itsu
    0.06
    Classic
    0.06
     Lor
    0.06
     Atom
    0.06
     Doors
    0.06
    chants
    0.06
    _ARRAY
    0.06
     Alma
    0.06
    Act Density 0.002%

    No Known Activations