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

    Neuronpedia

    INDEX
    Explanations

    Stokes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쒔
    -0.08
    科學
    -0.08
    obutton
    -0.07
    _tokenize
    -0.07
     batting
    -0.07
     Walnut
    -0.07
    全面建成
    -0.07
     Ben
    -0.07
     layui
    -0.07
    .guard
    -0.07
    POSITIVE LOGITS
    roe
    0.08
     ais
    0.07
    ente
    0.07
     Demo
    0.07
    (↵
    0.07
    ate
    0.07
    imet
    0.06
    קשה
    0.06
     Abram
    0.06
    .)↵
    0.06
    Act Density 0.001%

    No Known Activations