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

    Neuronpedia

    INDEX
    Explanations

    concisely structured statements and inquiries related to practical concerns or procedural information

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

    Concluding adverbs and discourse markers

    np_acts-logits-general · gemini-2.0-flash

    sentence endings and summaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    новништво
    -0.47
    arschu
    -0.42
     urmă
    -0.41
    ')):
    -0.40
     initComponents
    -0.40
    adə
    -0.40
     filósofo
    -0.39
     asiática
    -0.39
    };*/
    -0.38
    >--}}
    -0.37
    POSITIVE LOGITS
     Overall
    0.68
    Overall
    0.65
     overall
    0.65
     Finally
    0.64
    Bref
    0.61
     Altogether
    0.60
    overall
    0.60
     finally
    0.57
    Finally
    0.56
     Lastly
    0.56
    Act Density 0.519%

    No Known Activations