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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax elements or structures

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

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.78
    principalTable
    -0.71
    脚注の使い方
    -0.65
     queſta
    -0.61
    𓂸
    -0.59
     BoxDecoration
    -0.59
    writeFieldEnd
    -0.59
    HideFlags
    -0.58
     gynhyrchwyd
    -0.58
    AddTagHelper
    -0.58
    POSITIVE LOGITS
     simply
    0.31
     version
    0.31
    putExtra
    0.29
    期刊论文
    0.28
    isRequired
    0.28
    oded
    0.27
    ीडियो
    0.27
     steckt
    0.27
    fin
    0.27
    คร
    0.27
    Act Density 0.035%

    No Known Activations