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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مشار
    -0.07
     elabor
    -0.07
     IEEE
    -0.07
     erv
    -0.06
    CppMethod
    -0.06
    >s
    -0.06
    _epsilon
    -0.06
    ，其中
    -0.06
    celik
    -0.06
     thereof
    -0.06
    POSITIVE LOGITS
     ON
    0.08
     Fiscal
    0.07
    ↵	↵
    0.06
    Instant
    0.06
    FLAGS
    0.06
    kerja
    0.06
     سپ
    0.06
    INIT
    0.06
     LENG
    0.06
    _content
    0.06
    Act Density 0.003%

    No Known Activations