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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сп
    -0.07
    ॉट
    -0.06
     اعتماد
    -0.06
    .INTERNAL
    -0.06
    ระ
    -0.06
     offre
    -0.06
    /apache
    -0.06
     parental
    -0.06
    ATAR
    -0.06
    ıcı
    -0.06
    POSITIVE LOGITS
     parameter
    0.07
     etc
    0.06
     Gifts
    0.06
    %'↵
    0.06
     Majority
    0.06
    DataBase
    0.06
     Counties
    0.06
     beans
    0.06
     Steak
    0.06
    -input
    0.06
    Act Density 0.003%

    No Known Activations