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

    Neuronpedia

    INDEX
    Explanations

    numeric types and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wetting
    0.43
     wet
    0.40
     McClellan
    0.39
     wetland
    0.38
     strings
    0.36
     комплекс
    0.36
    めます
    0.36
     glycoprotein
    0.36
     factoryName
    0.36
    迎え
    0.36
    POSITIVE LOGITS
    Numeric
    0.97
     numeric
    0.96
    数値
    0.94
     integer
    0.92
    numeric
    0.90
    数字
    0.90
     숫자
    0.90
    Integer
    0.90
     Numeric
    0.89
    數字
    0.88
    Act Density 0.027%

    No Known Activations