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

    Neuronpedia

    INDEX
    Explanations

    configure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     battles
    -0.08
    Call
    -0.07
    细
    -0.07
     orbital
    -0.07
     imaging
    -0.07
    .bar
    -0.07
     Rim
    -0.07
    tau
    -0.07
     Bank
    -0.07
     introducing
    -0.07
    POSITIVE LOGITS
    frey
    0.07
    -small
    0.07
     preferably
    0.07
     içer
    0.07
    私服
    0.07
    вещ
    0.06
    貅
    0.06
    <path
    0.06
    פרו
    0.06
    겍
    0.06
    Act Density 0.006%

    No Known Activations