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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by units or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Medal
    0.43
     erm
    0.40
    皿
    0.38
     banner
    0.37
     Nok
    0.36
     traveller
    0.35
     বাসিন্দ
    0.35
    лимпий
    0.35
     mist
    0.35
     выход
    0.35
    POSITIVE LOGITS
    シャレ
    0.42
    遶
    0.40
     Gregorio
    0.40
    figs
    0.40
    کر
    0.39
     লাইন
    0.38
    ionis
    0.38
    𒁀
    0.38
     gpio
    0.38
     समित
    0.37
    Act Density 0.007%

    No Known Activations