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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming syntax and structure

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

    code symbols like `=` and `;`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.59
     Италијани
    -0.57
    Autoritní
    -0.56
     balsam
    -0.55
     fieldName
    -0.55
     pulso
    -0.54
     poffe
    -0.54
     censiti
    -0.53
    Билгалдахарш
    -0.53
    <pad>
    -0.52
    POSITIVE LOGITS
    addPreferredGap
    0.38
    ValueGenerated
    0.33
    styleType
    0.32
     khỏi
    0.31
    QMetaType
    0.31
     fail
    0.29
    <%=
    0.29
    mezzo
    0.28
     Crock
    0.27
     jLabel
    0.27
    Act Density 0.013%

    No Known Activations