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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Deploy
    -0.07
     venda
    -0.07
     sweet
    -0.07
     exits
    -0.07
     sudden
    -0.07
    appear
    -0.07
     teen
    -0.07
    eature
    -0.06
    呼
    -0.06
     Ext
    -0.06
    POSITIVE LOGITS
    옙
    0.08
     orchestr
    0.08
     resultSet
    0.08
    חומרים
    0.08
     нуж
    0.08
     случа
    0.08
    cob
    0.07
     kvinnor
    0.07
     Basel
    0.07
     zobac
    0.07
    Act Density 0.000%

    No Known Activations