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

    Neuronpedia

    INDEX
    Explanations

    even though

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    甚至
    1.45
     bahkan
    1.44
    Either
    1.35
     Either
    1.32
    とにかく
    1.32
     Bahkan
    1.32
     thậm
    1.29
     également
    1.27
    甚至是
    1.26
     даже
    1.21
    POSITIVE LOGITS
     though
    2.58
    Though
    1.73
    though
    1.71
     tho
    1.58
     Though
    1.56
     несмотря
    1.41
     amidst
    1.32
    handedly
    1.31
     without
    1.29
     considering
    1.18
    Act Density 0.070%

    No Known Activations