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
     >
    -0.97
     )
    -0.82
     Up
    -0.79
    Up
    -0.69
     up
    -0.65
     ),
    -0.58
    up
    -0.56
     );
    -0.52
     module
    -0.52
    ly
    -0.52
    POSITIVE LOGITS
     للاسماء
    1.36
     Roskov
    1.24
    GEBURTSDATUM
    1.20
    InjectAttribute
    1.20
     estekak
    1.18
     beginnetje
    1.16
    expandindo
    1.15
    SharedDtor
    1.15
     архивлан
    1.14
     tartalomajánló
    1.13
    Act Density 0.108%

    No Known Activations