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
     Dom
    -0.07
    -li
    -0.07
     mest
    -0.06
    _singleton
    -0.06
    -translate
    -0.06
    GetInstance
    -0.06
    řil
    -0.06
     Nie
    -0.06
    liğinin
    -0.06
    ล
    -0.06
    POSITIVE LOGITS
     worn
    0.08
     motorcycle
    0.07
     тр
    0.06
    ARING
    0.06
    .addTab
    0.06
    Db
    0.06
     انقلاب
    0.06
     пункт
    0.06
     Ellie
    0.06
    ollision
    0.06
    Act Density 0.031%

    No Known Activations