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

    Neuronpedia

    INDEX
    Explanations

    statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .JMenuItem
    -0.07
    irá
    -0.06
     faulty
    -0.06
    十分
    -0.06
     Continent
    -0.06
    ุลาคม
    -0.06
    _random
    -0.06
     привы
    -0.06
     chẳng
    -0.06
     mutex
    -0.06
    POSITIVE LOGITS
     exported
    0.07
    Aligned
    0.06
     мик
    0.06
     gt
    0.06
    nuts
    0.06
    니다
    0.06
    shi
    0.06
     stressing
    0.06
    isol
    0.06
     esp
    0.06
    Act Density 0.019%

    No Known Activations