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

    Neuronpedia

    INDEX
    Explanations

    specific formatting and structural elements typically found in technical documents or code

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

    Dates with numbers

    np_acts-logits-general · gemini-2.0-flash

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Geſch
    -0.73
     ddelwed
    -0.72
    <unused79>
    -0.72
    <unused43>
    -0.72
    pecabe
    -0.72
    <unused80>
    -0.72
    <unused16>
    -0.72
    <unused41>
    -0.71
    <unused23>
    -0.71
    <unused8>
    -0.71
    POSITIVE LOGITS
     morning
    0.42
     day
    0.39
     afternoon
    0.39
    Kjelder
    0.37
     date
    0.36
    day
    0.36
    Date
    0.36
     evening
    0.35
     (
    0.35
     Tages
    0.34
    Act Density 0.196%

    No Known Activations