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

    Neuronpedia

    INDEX
    Explanations

    non-english

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dictions
    -0.07
    送料無料
    -0.07
     Clan
    -0.07
     cán
    -0.06
    fin
    -0.06
    -Jan
    -0.06
    lobs
    -0.06
     basın
    -0.06
    ศจ
    -0.06
     arcs
    -0.06
    POSITIVE LOGITS
     Scr
    0.07
    144
    0.07
    iosper
    0.06
    ičky
    0.06
     supper
    0.06
    Ř
    0.06
     bedroom
    0.06
    어
    0.06
    Veter
    0.06
    >";↵
    0.06
    Act Density 0.007%

    No Known Activations