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

    Neuronpedia

    INDEX
    Explanations

    roles and professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    0.48
    language
    0.44
    Language
    0.42
    ní
    0.40
    nove
    0.40
    re
    0.39
    glicherweise
    0.39
    ended
    0.38
    ኔ
    0.38
    étale
    0.38
    POSITIVE LOGITS
     ماحول
    0.46
     هستیم
    0.40
     ဒ
    0.38
     целях
    0.37
     tại
    0.37
     năm
    0.36
     μέχρι
    0.36
     cũng
    0.36
     က
    0.36
     Lyft
    0.36
    Act Density 0.001%

    No Known Activations