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

    Neuronpedia

    INDEX
    Explanations

    function return values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Parameters
    0.55
    Arguments
    0.52
    parameters
    0.49
    PARAMETER
    0.48
    Parameters
    0.48
     parameter
    0.47
     arguments
    0.45
     参数
    0.44
     parametros
    0.44
     parameters
    0.44
    POSITIVE LOGITS
    return
    0.50
     returns
    0.45
     return
    0.44
    returns
    0.42
    帰
    0.39
    Returns
    0.39
     resulta
    0.39
     volta
    0.39
     ట
    0.38
     retorna
    0.37
    Act Density 0.014%

    No Known Activations