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

    Neuronpedia

    INDEX
    Explanations

    depends on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    efficient
    0.31
     tomto
    0.30
    创建一个
    0.29
     unui
    0.29
    ddar
    0.29
     hervorrag
    0.29
    ంతో
    0.28
    mkdir
    0.28
     photosynthesis
    0.28
     новом
    0.28
    POSITIVE LOGITS
     type
    0.70
    类型
    0.58
     tipo
    0.56
    ประเภท
    0.56
    type
    0.52
     típus
    0.52
     rodzaj
    0.52
     типу
    0.52
     종류
    0.52
     प्रकार
    0.51
    Act Density 1.401%

    No Known Activations