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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crc
    -0.07
     детей
    -0.07
    precision
    -0.07
     привы
    -0.06
     lexical
    -0.06
    음을
    -0.06
     incon
    -0.06
     attenu
    -0.06
    پی
    -0.06
     其
    -0.06
    POSITIVE LOGITS
    Flow
    0.07
     Statistical
    0.06
     Transit
    0.06
    now
    0.06
    تدى
    0.06
     Н
    0.06
     Estimates
    0.06
    .allowed
    0.06
    _PREFIX
    0.06
     Nutrition
    0.05
    Act Density 0.293%

    No Known Activations