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

    Neuronpedia

    INDEX
    Explanations

    professional job titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.29
    ?
    0.28
    ले
    0.27
    !
    0.27
    on
    0.26
    taker
    0.26
    芋
    0.25
    กัน
    0.25
    نا
    0.25
    ت
    0.24
    POSITIVE LOGITS
    工程师
    0.27
    મ
    0.27
     Year
    0.26
    ことにより
    0.26
     songwriter
    0.26
    ъ
    0.25
    𝗈
    0.25
     الذين
    0.25
    c
    0.25
    ទទួល
    0.25
    Act Density 0.259%

    No Known Activations