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

    Neuronpedia

    INDEX
    Explanations

    converting between fractions and decimals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anthracene
    0.39
     addicts
    0.38
    的意思
    0.37
     addict
    0.37
     куда
    0.36
    proteins
    0.36
    brains
    0.36
     орган
    0.36
     assumption
    0.35
    μφωνα
    0.35
    POSITIVE LOGITS
    Conversion
    0.43
     linguaggio
    0.43
     Percent
    0.42
     Converting
    0.42
     Conversion
    0.41
     Cycling
    0.41
     Petr
    0.38
     Manip
    0.38
     conversión
    0.38
     کبھی
    0.38
    Act Density 0.001%

    No Known Activations