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

    Neuronpedia

    INDEX
    Explanations

    number of parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Homestead
    0.43
    0.42
    铡
    0.42
     किफ
    0.42
    نیٹ
    0.41
     homestead
    0.40
     geeign
    0.40
     Poverty
    0.40
    দ্দি
    0.39
    लाभ
    0.39
    POSITIVE LOGITS
     weights
    1.00
     parameters
    0.96
    Weights
    0.84
    weights
    0.83
     parameter
    0.81
    parameters
    0.81
    參數
    0.80
     weight
    0.78
     Parameters
    0.78
    参数
    0.77
    Act Density 0.059%

    No Known Activations