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

    Neuronpedia

    INDEX
    Explanations

    physics, vacuum expectation values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     السلط
    -0.07
    톈
    -0.07
    疏散
    -0.07
    湣
    -0.07
    社会组织
    -0.07
     minors
    -0.06
    ዳ
    -0.06
     licences
    -0.06
     пес
    -0.06
    漫步
    -0.06
    POSITIVE LOGITS
    <div
    0.08
    (driver
    0.07
    _args
    0.07
    div
    0.07
    >>()
    0.07
    니까
    0.07
     Decode
    0.07
    <HashMap
    0.07
    جر
    0.06
     transformer
    0.06
    Act Density 0.008%

    No Known Activations