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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    connect
    -0.07
     Celebrity
    -0.07
    ereg
    -0.06
     stations
    -0.06
     Decide
    -0.06
     FileWriter
    -0.06
    -Cds
    -0.06
     mission
    -0.06
     Bachelor
    -0.06
     Strategy
    -0.06
    POSITIVE LOGITS
     yaz
    0.08
     размещ
    0.07
    urther
    0.06
     jub
    0.06
    ''"
    0.06
     rushes
    0.06
    :last
    0.06
     Bav
    0.06
    )))),
    0.06
    ificantly
    0.06
    Act Density 0.094%

    No Known Activations