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

    Neuronpedia

    INDEX
    Explanations

    equilibrium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ymm
    -0.08
    _PAY
    -0.07
     Discount
    -0.07
    компонент
    -0.07
    exist
    -0.07
    Girl
    -0.07
     Super
    -0.06
     Polyester
    -0.06
     Spa
    -0.06
     Frontier
    -0.06
    POSITIVE LOGITS
    	table
    0.08
    第一时间
    0.07
    蘧
    0.07
    🌑
    0.07
    .setRotation
    0.07
    ("")↵
    0.07
    战术
    0.07
    //--------------------------------
    0.07
    ically
    0.07
    itial
    0.07
    Act Density 0.010%

    No Known Activations