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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kle
    -0.08
     �
    -0.07
    <TSource
    -0.07
    🏪
    -0.07
    [table
    -0.07
     Wyn
    -0.07
    아버
    -0.07
    춤
    -0.07
     הזכויות
    -0.07
     Kelly
    -0.07
    POSITIVE LOGITS
     moved
    0.07
    dos
    0.07
    🚣
    0.07
    �
    0.07
     Shower
    0.06
     Editorial
    0.06
    PAT
    0.06
    ラー
    0.06
     תהיה
    0.06
    DIC
    0.06
    Act Density 0.005%

    No Known Activations