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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals and their associated contexts

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

    roman numerals and alphabet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.78
     $_=
    -0.73
    httphttps
    -0.73
     fashiola
    -0.71
     $_-
    -0.71
    majánló
    -0.70
    <unused14>
    -0.69
    <unused28>
    -0.69
    <unused23>
    -0.69
    [@BOS@]
    -0.69
    POSITIVE LOGITS
     roman
    0.33
     Roman
    0.31
     płyn
    0.31
    Roman
    0.28
     jednotliv
    0.26
     texturas
    0.25
    age
    0.25
    document
    0.24
     romanos
    0.23
    text
    0.22
    Act Density 0.006%

    No Known Activations