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

    Neuronpedia

    INDEX
    Explanations

    As

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    预览
    -0.07
     DNC
    -0.06
    ến
    -0.06
     gz
    -0.06
    :new
    -0.06
    [end
    -0.06
    能够
    -0.06
    tura
    -0.06
    يو
    -0.06
     넘
    -0.06
    POSITIVE LOGITS
     As
    0.08
     веществ
    0.07
    IS
    0.06
    sidebar
    0.06
    .Inter
    0.06
    以来
    0.06
    _without
    0.06
    πουλος
    0.06
     منط
    0.06
     باشگاه
    0.06
    Act Density 0.002%

    No Known Activations