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

    Neuronpedia

    INDEX
    Explanations

    school and university names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ı
    1.58
    ної
    1.53
    но
    1.51
    وك
    1.45
    蜢
    1.45
    ırd
    1.41
    р
    1.32
    ished
    1.30
    습니다
    1.30
    ą
    1.28
    POSITIVE LOGITS
    goers
    1.60
    ک
    1.34
    ties
    1.27
    其他
    1.26
     jerseys
    1.25
    mates
    1.20
    ting
    1.16
    OOL
    1.11
    Celsius
    1.11
    them
    1.09
    Act Density 0.052%

    No Known Activations