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

    Neuronpedia

    INDEX
    Explanations

    dtype assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contoured
    0.43
    Cock
    0.43
    Lincoln
    0.40
     পায়ের
    0.39
     ম্যাক
    0.38
    臭
    0.38
     mùi
    0.38
    Approximately
    0.37
     geometrical
    0.37
    Version
    0.37
    POSITIVE LOGITS
     dtype
    0.92
    dtype
    0.81
     dataType
    0.70
    dataType
    0.69
     datatype
    0.69
    datatype
    0.68
    float
    0.65
    DataType
    0.65
     float
    0.65
     DataType
    0.60
    Act Density 0.017%

    No Known Activations