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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Programm
    -0.07
    -LAST
    -0.07
     Locale
    -0.07
    èo
    -0.06
    销售
    -0.06
    庫
    -0.06
    _repo
    -0.06
     кто
    -0.06
     pazar
    -0.06
     Mond
    -0.06
    POSITIVE LOGITS
     ply
    0.07
     appreciated
    0.06
    OLUTION
    0.06
     struck
    0.06
     словами
    0.06
    rish
    0.06
     appreciate
    0.06
     twisting
    0.06
    ="__
    0.06
    inating
    0.06
    Act Density 0.000%

    No Known Activations