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

    Neuronpedia

    INDEX
    Explanations

    the presence of multi-character whitespace sequences in the text

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

    programming keywords and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.56
     onBind
    -0.55
    WriteBarrier
    -0.53
     forState
    -0.52
    下载附件
    -0.49
     vérit
    -0.48
    EndContext
    -0.46
    extAlignment
    -0.46
    ieteur
    -0.46
     ostavi
    -0.46
    POSITIVE LOGITS
    MessageOf
    0.48
     Réponses
    0.45
    contentLoaded
    0.45
     initComponents
    0.42
    oredCriteria
    0.41
    Personendaten
    0.41
    <bos>
    0.39
     AspNetCore
    0.38
    ↹
    0.38
     Beagle
    0.37
    Act Density 0.009%

    No Known Activations