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

    Neuronpedia

    INDEX
    Explanations

    commas, and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    steen
    -0.08
    spar
    -0.08
     Spir
    -0.07
     mex
    -0.07
    definition
    -0.06
    .SET
    -0.06
    北京时间
    -0.06
    ệnh
    -0.06
    詩
    -0.06
    Directory
    -0.06
    POSITIVE LOGITS
    عرف
    0.07
    Split
    0.07
    Ins
    0.07
    עניינ
    0.07
    얻
    0.06
    tw
    0.06
    namespace
    0.06
     Raise
    0.06
     utiliz
    0.06
    Lic
    0.06
    Act Density 0.002%

    No Known Activations