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

    Neuronpedia

    INDEX
    Explanations

    thinker

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    worker
    -0.78
     Dyer
    -0.77
     Player
    -0.76
    klart
    -0.75
     geweest
    -0.71
     thinker
    -0.69
     goutte
    -0.69
     communicator
    -0.68
     Producción
    -0.68
     sfera
    -0.68
    POSITIVE LOGITS
     typelib
    0.57
    adpleegd
    0.51
    UnusedPrivate
    0.48
    startActivity
    0.48
     tras
    0.46
     الحره
    0.44
     wah
    0.44
     to
    0.44
     social
    0.43
     ImGui
    0.43
    Act Density 0.240%

    No Known Activations