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

    Neuronpedia

    INDEX
    Explanations

    only first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     queryset
    -0.07
    .exchange
    -0.07
    interest
    -0.06
    .ke
    -0.06
     insp
    -0.06
    мон
    -0.06
    firefox
    -0.06
    .Sum
    -0.06
     wszyst
    -0.06
     Angebot
    -0.06
    POSITIVE LOGITS
    确
    0.07
     спос
    0.06
    (confirm
    0.06
    ラー
    0.06
     ничего
    0.06
    ıl
    0.06
     discriminatory
    0.06
     (=
    0.06
    лось
    0.06
    iling
    0.06
    Act Density 0.007%

    No Known Activations