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

    Neuronpedia

    INDEX
    Explanations

    phrases that highlight the significance or importance of a topic

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

    importance and reasons why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.73
    Tikang
    -0.72
     propOrder
    -0.70
     estekak
    -0.65
    ſelben
    -0.62
     ſehen
    -0.61
     Taktlose
    -0.60
    INCREF
    -0.58
    تفصیلات
    -0.58
     ſeinen
    -0.58
    POSITIVE LOGITS
     importance
    0.52
     purpose
    0.49
     significance
    0.46
     benefits
    0.43
     goal
    0.43
     goals
    0.42
     reason
    0.40
    Importance
    0.40
     reasons
    0.38
     Importance
    0.37
    Act Density 0.037%

    No Known Activations