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

    Neuronpedia

    INDEX
    Explanations

    numerical data and identifiers

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

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    majánló
    -0.72
     ſind
    -0.69
     パンチラ
    -0.68
    ſſung
    -0.68
    __':
    -0.68
     queſta
    -0.67
    ſcher
    -0.67
    <unused16>
    -0.67
     $_-
    -0.67
    <unused3>
    -0.66
    POSITIVE LOGITS
    ,
    0.48
    .
    0.42
     (
    0.40
     OFDb
    0.34
    IndentedString
    0.34
     Res
    0.33
     is
    0.32
    ;
    0.32
     -
    0.31
     res
    0.31
    Act Density 0.143%

    No Known Activations