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

    Neuronpedia

    INDEX
    Explanations

    angular app components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     potentials
    0.41
    essero
    0.40
    commonByteArray
    0.40
     antérieur
    0.38
    UnderWater
    0.38
    城県
    0.37
     পারবেন
    0.36
    ","#
    0.36
     sécrétion
    0.36
    買って
    0.36
    POSITIVE LOGITS
     shared
    0.49
     landen
    0.48
     Shared
    0.47
     Guards
    0.47
     Guard
    0.46
     condiv
    0.46
     Core
    0.44
    SHARED
    0.42
     './
    0.40
     Guarda
    0.40
    Act Density 0.003%

    No Known Activations