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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NamedQueries
    -0.72
    +#+#
    -0.52
     referenties
    -0.49
     än
    -0.47
     istrinya
    -0.47
    tem
    -0.47
     cesse
    -0.46
     denna
    -0.45
     suaminya
    -0.45
     this
    -0.44
    POSITIVE LOGITS
     pylori
    0.60
     Picchu
    0.60
    Portale
    0.59
     StatefulWidget
    0.58
     StatelessWidget
    0.57
    ToProps
    0.56
    LEncoder
    0.54
     שוליים
    0.53
    Salta
    0.52
     Hypers
    0.52
    Act Density 0.006%

    No Known Activations