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

    Neuronpedia

    INDEX
    Explanations

    goes beyond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     selain
    1.48
     instead
    1.31
     except
    1.24
     besides
    1.24
     вместо
    1.21
     Selain
    1.19
     Instead
    1.18
    instead
    1.15
    Besides
    1.14
    以外の
    1.14
    POSITIVE LOGITS
     beyond
    1.84
     Beyond
    1.62
    beyond
    1.61
    Beyond
    1.54
     far
    1.04
     dépasse
    1.04
     Far
    1.03
     transcends
    1.03
     allá
    1.03
     exceeds
    1.00
    Act Density 0.083%

    No Known Activations