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

    Neuronpedia

    INDEX
    Explanations

    Shiny finish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wield
    -0.07
    薩
    -0.06
    cnt
    -0.06
    .Mesh
    -0.06
     mesmer
    -0.06
    θ
    -0.06
     Peoples
    -0.06
     prof
    -0.06
    vision
    -0.06
    итися
    -0.06
    POSITIVE LOGITS
    一卷
    0.06
     İran
    0.06
     cabe
    0.06
    两
    0.06
     Česk
    0.06
     THREE
    0.06
     ΕΛ
    0.06
     daughters
    0.06
    退
    0.06
    .optimize
    0.06
    Act Density 0.029%

    No Known Activations