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

    Neuronpedia

    INDEX
    Explanations

    2 or 3

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    으로
    -0.07
    ('^
    -0.06
    ounty
    -0.06
    olas
    -0.06
    ходит
    -0.06
    นาม
    -0.06
    _lahir
    -0.06
    conut
    -0.06
     نموده
    -0.06
    torrent
    -0.06
    POSITIVE LOGITS
    危
    0.07
     ")";↵
    0.07
     suck
    0.06
     пон
    0.06
     Sto
    0.06
     brightest
    0.06
     Gene
    0.06
    agos
    0.06
     immature
    0.06
    Fee
    0.06
    Act Density 0.045%

    No Known Activations