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

    Neuronpedia

    INDEX
    Explanations

    people to, with, from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.88
    ം
    0.80
    u
    0.73
    ו
    0.71
    i
    0.69
    y
    0.68
    ل
    0.67
    it
    0.65
    in
    0.65
    ে
    0.64
    POSITIVE LOGITS
    𝙴
    0.54
     amelyek
    0.47
     którzy
    0.47
     пово
    0.46
    𝙙
    0.46
    𝙉
    0.45
    THE
    0.44
    ভাবে
    0.44
    STUD
    0.43
    ジェ
    0.43
    Act Density 0.219%

    No Known Activations