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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and structural elements in code

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

    source code includes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.33
     تضيفلها
    -0.31
    又不
    -0.29
    */].
    -0.29
     huom
    -0.27
    -0.27
    )=>
    -0.26
    EndContext
    -0.26
     sil
    -0.26
     le
    -0.26
    POSITIVE LOGITS
    UnusedPrivate
    0.85
    VersionUID
    0.66
    richTextPanel
    0.60
    URLException
    0.55
    expandindo
    0.54
     vooz
    0.54
     fashiola
    0.54
    ꪳ
    0.54
    dientemente
    0.54
    parsedMessage
    0.53
    Act Density 0.020%

    No Known Activations