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

    Neuronpedia

    INDEX
    Explanations

    direct speech and quotations in the text

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

    Quotation marks followed by pronouns

    np_acts-logits-general · gemini-2.0-flash

    statement opener

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.82
     pinulongan
    -0.66
     noDo
    -0.66
    ंदीखरीदारी
    -0.65
     AssemblyCompany
    -0.63
    PerformLayout
    -0.63
    addContainerGap
    -0.62
    期刊论文
    -0.62
     المعيارى
    -0.60
     intStringLen
    -0.60
    POSITIVE LOGITS
     success
    0.35
     geest
    0.33
     enamor
    0.32
     réussi
    0.30
    ungkapkan
    0.29
     cuida
    0.29
    mockMvc
    0.29
     voul
    0.28
     succeeded
    0.28
     affaires
    0.28
    Act Density 0.151%

    No Known Activations