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

    Neuronpedia

    INDEX
    Explanations

    available for use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ి
    1.34
    즈
    1.26
    잘
    1.19
    የ
    1.19
     이어
    1.14
    事实
    1.14
    an
    1.14
    最初に
    1.14
    тель
    1.14
    ed
    1.14
    POSITIVE LOGITS
    to
    1.41
    nement
    1.25
     कराए
    1.24
     કરાવ
    1.22
    anaa
    1.22
     chlorine
    1.21
     продаже
    1.17
    amins
    1.17
    ties
    1.15
    ৈধ
    1.13
    Act Density 0.094%

    No Known Activations