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

    Neuronpedia

    INDEX
    Explanations

    Code Documentation Snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lena
    -0.07
    Six
    -0.07
    .Argument
    -0.07
    子宫
    -0.07
     chụp
    -0.07
    lığını
    -0.06
    .Navigator
    -0.06
     gioc
    -0.06
    เกาะ
    -0.06
     Georgetown
    -0.06
    POSITIVE LOGITS
    etre
    0.07
    .Expect
    0.07
    챦
    0.07
    一方面
    0.07
     зависит
    0.07
     colleagues
    0.07
     proxy
    0.06
    縱
    0.06
     SHORT
    0.06
     [...
    0.06
    Act Density 0.030%

    No Known Activations