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

    Neuronpedia

    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    データ
    -0.07
     '))↵
    -0.07
    DataProvider
    -0.07
     τρό
    -0.06
     ')[
    -0.06
     먼저
    -0.06
    .ForEach
    -0.06
     Gilbert
    -0.06
     έκ
    -0.06
    POSITIVE LOGITS
    ileş
    0.07
    (ierr
    0.07
    urniture
    0.07
    ışman
    0.07
     Extensions
    0.06
     average
    0.06
    ouns
    0.06
    President
    0.06
    plements
    0.06
    ُون
    0.06
    Act Density 0.000%

    No Known Activations