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

    Neuronpedia

    INDEX
    Explanations

    blog URLs and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    経営
    0.67
     "//
    0.66
     '//
    0.64
     electromagnetic
    0.63
     electronic
    0.63
     integer
    0.61
    http
    0.61
    integer
    0.60
     fö
    0.60
     electron
    0.59
    POSITIVE LOGITS
    TikTok
    1.08
     TikTok
    1.06
     Esports
    1.00
     tiktok
    0.95
     Lyft
    0.94
    🫠
    0.94
    preceq
    0.93
    tsv
    0.93
     Tiktok
    0.93
     rebuttal
    0.91
    Act Density 0.053%

    No Known Activations