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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insisting
    -0.07
    流淌
    -0.07
     SUV
    -0.06
    一抹
    -0.06
    +s
    -0.06
     RU
    -0.06
    -test
    -0.06
    dden
    -0.06
     maté
    -0.06
    𝑣
    -0.06
    POSITIVE LOGITS
    مح
    0.07
    ofile
    0.07
    太
    0.07
    .Compiler
    0.07
     получи
    0.07
    раниц
    0.07
    在于
    0.07
    都喜欢
    0.07
    元件
    0.07
     Finished
    0.07
    Act Density 0.002%

    No Known Activations