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

    Neuronpedia

    INDEX
    Explanations

    imper

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DISTRIBUT
    -0.08
    ="${
    -0.08
    .splitext
    -0.07
    ЛО
    -0.07
     Sponge
    -0.07
    -F
    -0.07
    -With
    -0.07
     explanation
    -0.07
    消化
    -0.07
    ◙
    -0.07
    POSITIVE LOGITS
     Imper
    0.07
    sup
    0.07
    婊
    0.07
     scripted
    0.07
     imper
    0.07
     bankers
    0.07
     humane
    0.07
    。。
    0.07
     Westminster
    0.07
     demanding
    0.07
    Act Density 0.004%

    No Known Activations