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

    Neuronpedia

    INDEX
    Explanations

    etc. and so on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ло
    1.17
    م
    1.15
    ン
    1.09
    ра
    1.05
    这个
    1.02
    نن
    1.02
    من
    1.02
    ان
    1.01
    𝙉
    1.01
    SON
    1.00
    POSITIVE LOGITS
    etera
    1.42
    등
    1.14
    方面的
    1.05
    등학교
    0.86
    々は
    0.84
     scriptures
    0.82
     nape
    0.82
     consenting
    0.82
     nutrients
    0.80
    于是
    0.80
    Act Density 0.003%

    No Known Activations