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

    Neuronpedia

    INDEX
    Explanations

    iterative methods, convolution, CUDA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Commissioners
    0.39
     TEST
    0.39
     Ware
    0.38
     Francisco
    0.37
     fiestas
    0.36
     minib
    0.36
     llave
    0.36
    APOLIS
    0.36
     متاثر
    0.36
     Artisan
    0.36
    POSITIVE LOGITS
     совме
    0.39
    痠
    0.38
     defies
    0.37
     వివర
    0.37
     несо
    0.37
    enrich
    0.37
    Detail
    0.36
    opathic
    0.36
     разобраться
    0.36
    mac
    0.36
    Act Density 0.000%

    No Known Activations