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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilder
    -0.07
    علی
    -0.06
     الم
    -0.06
    ucursal
    -0.06
     गत
    -0.06
     mar
    -0.06
    淡
    -0.06
     chromium
    -0.06
    iplina
    -0.06
    直
    -0.06
    POSITIVE LOGITS
    _ble
    0.07
    OME
    0.07
    ome
    0.07
     heterogeneous
    0.06
    Background
    0.06
    (sess
    0.06
     Mathematics
    0.06
     Psychology
    0.06
     ////
    0.06
     subsidies
    0.06
    Act Density 0.000%

    No Known Activations