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

    Neuronpedia

    INDEX
    Explanations

    obj

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yên
    -0.07
     hotline
    -0.06
    john
    -0.06
    ade
    -0.06
     hlavu
    -0.06
    เลย
    -0.06
    idade
    -0.06
     retreat
    -0.06
    เว
    -0.06
    소년
    -0.06
    POSITIVE LOGITS
    """↵↵
    0.07
    Sports
    0.07
    eceği
    0.06
    Vintage
    0.06
    ...</
    0.06
    .Endpoint
    0.06
    性能
    0.06
    silver
    0.06
    GetInstance
    0.06
     sincerely
    0.06
    Act Density 0.001%

    No Known Activations