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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and possibly indicators of personal experience or involvement

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

    document references and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parametrize
    -0.57
    ReusableCell
    -0.52
    AccessorTable
    -0.50
     ListTile
    -0.45
    summary
    -0.44
     SUMMARY
    -0.42
     StringTokenizer
    -0.42
     summaries
    -0.41
     summary
    -0.41
    picasso
    -0.40
    POSITIVE LOGITS
     document
    0.59
     documento
    0.52
    #
    0.48
     template
    0.47
    ไฟ
    0.47
     file
    0.47
     compila
    0.46
    documentclass
    0.45
     Dokumente
    0.45
     dokumen
    0.45
    Act Density 0.001%

    No Known Activations