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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transition phrases that indicate conclusions or results

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

    Follows "therefore" or "hence"

    np_acts-logits-general · gemini-2.0-flash

    signals conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BrowserModule
    -0.78
    رشف
    -0.76
     OTHERWISE
    -0.76
    providedIn
    -0.72
    TagMode
    -0.70
     yourselves
    -0.65
     Monfieur
    -0.65
     FIXME
    -0.65
    welli
    -0.65
     Efq
    -0.64
    POSITIVE LOGITS
     when
    0.61
    invokeLater
    0.58
     it
    0.55
     if
    0.55
    LoadScene
    0.54
    ,
    0.54
     MenuView
    0.54
    حوالہ
    0.53
    Kjelder
    0.52
     whenever
    0.52
    Act Density 0.417%

    No Known Activations