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

    Neuronpedia

    INDEX
    Explanations

    Chinese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Reuters
    -0.07
     �
    -0.07
    체
    -0.07
     governance
    -0.06
    coded
    -0.06
    curr
    -0.06
    .identity
    -0.06
    _avg
    -0.06
    "For
    -0.06
    YRO
    -0.06
    POSITIVE LOGITS
     missionaries
    0.07
     Checking
    0.07
     doors
    0.06
     beide
    0.06
     vytvoř
    0.06
    _views
    0.06
     应
    0.06
    sc
    0.06
    ･･
    0.06
    حم
    0.06
    Act Density 0.003%

    No Known Activations