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

    Neuronpedia

    INDEX
    Explanations

    structure and syntax elements related to programming and code constructs

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

    code and math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.82
    fromnode
    -0.80
    transQ
    -0.73
     queſta
    -0.71
     $_(
    -0.70
    ſelves
    -0.69
     $_"
    -0.69
     itſelf
    -0.69
    <unused14>
    -0.69
    <unused16>
    -0.69
    POSITIVE LOGITS
     հղումներ
    0.40
     للاسماء
    0.39
     sha
    0.36
    findpost
    0.36
    发表于
    0.35
    leistung
    0.34
     autorytatywna
    0.33
    .....
    0.31
    …..
    0.31
    Thankyou
    0.31
    Act Density 0.072%

    No Known Activations