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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    汝
    -0.06
     ith
    -0.06
    ือน
    -0.06
    .ListBox
    -0.06
    lac
    -0.06
    igner
    -0.06
    .collections
    -0.06
     Faith
    -0.06
    同心
    -0.06
     Koh
    -0.06
    POSITIVE LOGITS
    껄
    0.08
     affair
    0.07
    라고
    0.07
     obstruction
    0.07
     signature
    0.07
     Avatar
    0.07
     burst
    0.07
    统计局
    0.07
    Widgets
    0.07
    stim
    0.07
    Act Density 0.020%

    No Known Activations