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

    Neuronpedia

    INDEX
    Explanations

    Web page snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $update
    -0.07
    eton
    -0.07
     conte
    -0.07
    Ale
    -0.07
    mín
    -0.06
     aster
    -0.06
    ially
    -0.06
    IMATE
    -0.06
    olland
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    .Head
    0.07
    >\
    0.07
    ....
    0.06
    Dashboard
    0.06
     timeframe
    0.06
     persecution
    0.06
    ,_
    0.06
     geh
    0.06
    MODULE
    0.06
    バイ
    0.06
    Act Density 0.174%

    No Known Activations