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

    Neuronpedia

    INDEX
    Explanations

    entries related to structured data or programming code attributes

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

    content and value fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.93
    featureID
    -0.85
    المشاركات
    -0.79
     ProtoMessage
    -0.78
     getItemId
    -0.77
    OGND
    -0.77
     betweenstory
    -0.76
     Italijanski
    -0.75
     InputDecoration
    -0.73
    脚注の使い方
    -0.71
    POSITIVE LOGITS
     content
    0.49
     itself
    0.46
    内容
    0.45
    內容
    0.42
     value
    0.39
    content
    0.39
     内容
    0.38
     selve
    0.38
    本身
    0.38
     actual
    0.38
    Act Density 0.085%

    No Known Activations