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

    Neuronpedia

    INDEX
    Explanations

    incorrect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defects
    -0.08
    网易
    -0.08
     Florence
    -0.07
    _NAV
    -0.07
    เ�
    -0.07
     lexical
    -0.07
     violet
    -0.07
     bulundu
    -0.07
    іль
    -0.07
     outer
    -0.07
    POSITIVE LOGITS
    大会
    0.09
     makah
    0.09
     bent
    0.08
     distancing
    0.08
    .maps
    0.08
     responsibly
    0.08
     skincare
    0.08
     कहानी
    0.08
     கூட
    0.08
     toka
    0.07
    Act Density 0.001%

    No Known Activations