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

    Neuronpedia

    INDEX
    Explanations

    freeCodeCamp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑟
    1.00
    𝑛
    0.95
     beiden
    0.95
    𝑑
    0.90
    𝑒
    0.90
     insbesondere
    0.88
    𝑃
    0.87
    𝐼
    0.86
     milij
    0.86
     viven
    0.85
    POSITIVE LOGITS
    ть
    0.78
    cknowled
    0.77
    ação
    0.75
    ін
    0.73
     impregnated
    0.71
    ಗಾರ
    0.68
    ରି
    0.67
    on
    0.64
    ים
    0.64
    itical
    0.64
    Act Density 0.003%

    No Known Activations