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

    Neuronpedia

    INDEX
    Explanations

    references to scientific papers and datasets

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

    arXiv references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChildIndex
    -0.38
     finnas
    -0.36
     Champlain
    -0.35
     initComponents
    -0.35
    Analytic
    -0.34
    DoubleQuotes
    -0.33
     analytic
    -0.33
    BagConstraints
    -0.32
    Batis
    -0.32
    quelize
    -0.32
    POSITIVE LOGITS
    arXiv
    0.91
    PhysRevD
    0.68
     arXiv
    0.63
    WaitGroup
    0.52
     oprot
    0.51
    下载附件
    0.51
    AndEndTag
    0.50
    Xiv
    0.49
     فريبيس
    0.49
    FileVersion
    0.48
    Act Density 0.660%

    No Known Activations