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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Roman" and its variations, particularly in historical or cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Rom, Roman, Roma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.50
    estries
    -0.44
     meille
    -0.44
    Билгалдахарш
    -0.42
    fowl
    -0.41
     iprot
    -0.41
     Hegel
    -0.41
     configureStore
    -0.41
    detectChanges
    -0.40
    quirrel
    -0.40
    POSITIVE LOGITS
     Roman
    0.96
     Rom
    0.93
    Rom
    0.93
    Roman
    0.92
     roman
    0.91
    roman
    0.90
     rom
    0.89
     ROM
    0.88
     Romano
    0.87
     ROMAN
    0.82
    Act Density 0.012%

    No Known Activations