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
     bei
    -0.07
     independence
    -0.07
     Assigned
    -0.07
    Ped
    -0.07
    _NONE
    -0.06
    empresa
    -0.06
     ghosts
    -0.06
     cages
    -0.06
     lifts
    -0.06
    .calendar
    -0.06
    POSITIVE LOGITS
     Law
    0.07
    实施
    0.06
     mantra
    0.06
    batis
    0.06
     imgs
    0.06
     law
    0.06
     soud
    0.06
     конкрет
    0.06
    ――――
    0.06
     =~
    0.06
    Act Density 0.002%

    No Known Activations