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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .take
    -0.06
    Range
    -0.06
     Williamson
    -0.06
     Development
    -0.06
     Bry
    -0.06
    Buf
    -0.06
     frequency
    -0.06
    车
    -0.06
    SimpleName
    -0.06
    Development
    -0.06
    POSITIVE LOGITS
     theaters
    0.06
    왔
    0.06
     ㅇㅇ
    0.06
    ái
    0.06
    ujete
    0.06
    .DateField
    0.06
    となり
    0.06
    /.↵
    0.06
    }`).
    0.06
    yeah
    0.06
    Act Density 0.020%

    No Known Activations