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

    Neuronpedia

    INDEX
    Explanations

    View

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ovém
    -0.06
    ma
    -0.06
     malfunction
    -0.06
     Salisbury
    -0.06
    ought
    -0.06
     embassy
    -0.06
     Incorporated
    -0.06
    underline
    -0.06
     revelations
    -0.06
    testdata
    -0.06
    POSITIVE LOGITS
    243
    0.07
    лев
    0.07
    jem
    0.07
     livelihood
    0.07
     view
    0.07
    [:]
    0.06
     makes
    0.06
     te
    0.06
     tableView
    0.06
    ��
    0.06
    Act Density 0.003%

    No Known Activations