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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Platform
    -0.09
    峥
    -0.09
    服务平台
    -0.08
    偻
    -0.07
    סכם
    -0.07
    恨
    -0.07
    نصف
    -0.07
    膝
    -0.07
    捕鱼
    -0.07
     tell
    -0.07
    POSITIVE LOGITS
     Existing
    0.08
    מחקר
    0.06
     //!
    0.06
     '/',
    0.06
    GER
    0.06
     overturned
    0.06
    .startDate
    0.06
     corpo
    0.06
     lexer
    0.06
    FD
    0.06
    Act Density 0.306%

    No Known Activations