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

    Neuronpedia

    INDEX
    Explanations

    references to specific software components and features in code

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

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     western
    -0.50
     Western
    -0.47
    <bos>
    -0.45
    western
    -0.44
    extérieur
    -0.44
     occidentale
    -0.43
     eastern
    -0.41
     loob
    -0.41
     caminh
    -0.41
    Western
    -0.41
    POSITIVE LOGITS
    arResult
    0.77
    jasmine
    0.56
    OCCURRED
    0.55
    mRecyclerView
    0.50
    lusconi
    0.50
    RTHOOK
    0.50
    下载附件
    0.49
     BorderSide
    0.48
    stateMutability
    0.47
    modelBuilder
    0.47
    Act Density 0.010%

    No Known Activations