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

    Neuronpedia

    INDEX
    Explanations

    CU

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CriticalSection
    -0.07
    宋体
    -0.07
    supplier
    -0.07
     bilir
    -0.07
    _NE
    -0.07
    cadena
    -0.06
    血
    -0.06
    orthand
    -0.06
    AAC
    -0.06
     redirectTo
    -0.06
    POSITIVE LOGITS
    elan
    0.07
    싸
    0.06
     locked
    0.06
    거
    0.06
    ]↵↵↵
    0.06
    렇
    0.06
     �
    0.06
     engage
    0.06
    IsValid
    0.06
     shy
    0.06
    Act Density 0.019%

    No Known Activations