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

    Neuronpedia

    INDEX
    Explanations

    try except block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tujuh
    0.70
     tuyến
    0.69
     MERCHANTABILITY
    0.69
     सोनी
    0.68
     effecting
    0.68
    ຜະລ
    0.68
     iPhones
    0.68
     Entries
    0.67
     zásob
    0.67
     Pond
    0.66
    POSITIVE LOGITS
    uana
    0.64
    部分
    0.60
     précédents
    0.59
    ্যতা
    0.59
     bisher
    0.59
    র্গে
    0.57
    کور
    0.57
    norr
    0.57
    urea
    0.56
     metam
    0.56
    Act Density 0.049%

    No Known Activations