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

    Neuronpedia

    INDEX
    Explanations

    writing excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arım
    -0.06
     쉬
    -0.06
     AC
    -0.06
    _EOL
    -0.06
    ¤¤
    -0.06
    -guid
    -0.06
    profits
    -0.06
     ActionBar
    -0.06
     Sandbox
    -0.06
     geliş
    -0.06
    POSITIVE LOGITS
    ,{"
    0.07
    ˜
    0.07
     fairness
    0.07
    (document
    0.06
     sexism
    0.06
    DES
    0.06
    更加
    0.06
     Hugo
    0.06
     MSC
    0.06
    CTX
    0.06
    Act Density 0.043%

    No Known Activations