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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olie
    -0.07
     č
    -0.07
     chiff
    -0.07
     Teil
    -0.07
    삼
    -0.07
    	File
    -0.07
     subt
    -0.07
     rouge
    -0.07
    齿
    -0.07
    íc
    -0.07
    POSITIVE LOGITS
    CppClass
    0.09
    buttonShape
    0.07
    廨
    0.07
     reloadData
    0.07
    classmethod
    0.07
    &)↵
    0.07
    战火
    0.07
    Politics
    0.07
    ])):↵
    0.07
    "]);↵
    0.07
    Act Density 0.003%

    No Known Activations