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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     superficial
    -0.07
    -West
    -0.07
     refriger
    -0.07
     visa
    -0.06
     increased
    -0.06
    Less
    -0.06
    Women
    -0.06
    \Php
    -0.06
     Fat
    -0.06
     redistribution
    -0.06
    POSITIVE LOGITS
    trecht
    0.07
    _MESH
    0.06
    canonical
    0.06
    ذا
    0.06
    _PREFIX
    0.06
    參
    0.06
    launch
    0.06
     cenu
    0.06
     ************************
    0.06
     ani
    0.06
    Act Density 0.020%

    No Known Activations