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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and terminology

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

    stat tags, mathit, Tag objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oa̍t
    -0.79
     surla
    -0.74
     Roskov
    -0.71
     Biôgrafia
    -0.71
    parsedMessage
    -0.70
     queſta
    -0.67
    arangay
    -0.66
     يتيمه
    -0.66
     snippetHide
    -0.64
     Italijani
    -0.64
    POSITIVE LOGITS
    <strong>
    0.37
    ...
    0.35
     e
    0.35
    1
    0.34
    I
    0.34
    2
    0.33
    A
    0.33
     
    0.33
     most
    0.33
    _
    0.33
    Act Density 0.101%

    No Known Activations