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

    Neuronpedia

    INDEX
    Explanations

    quantity and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oppure
    0.15
     котором
    0.15
     której
    0.14
     अथवा
    0.14
     which
    0.14
     którego
    0.14
     with
    0.13
     hoặc
    0.13
     Also
    0.13
    atau
    0.13
    POSITIVE LOGITS
     types
    0.28
     aspects
    0.28
     kinds
    0.28
    类型的
    0.26
    不同的
    0.26
     different
    0.24
     प्रकारचे
    0.23
     аспек
    0.23
    方面的
    0.21
     diferentes
    0.21
    Act Density 0.101%

    No Known Activations