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

    Neuronpedia

    INDEX
    Explanations

    contrasting statements or situations

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

    Follows "but" or periods

    np_acts-logits-general · gemini-2.0-flash

    contrasting or qualifying statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.83
    sizeCache
    -0.80
     >=",
    -0.79
     <>",
    -0.77
    webElementGuid
    -0.71
    -0.69
    SequentialGroup
    -0.69
    VYMaps
    -0.67
    Rhestr
    -0.66
    RTDA
    -0.66
    POSITIVE LOGITS
     overall
    3.22
     Overall
    2.96
    Overall
    2.90
    overall
    2.90
    总体
    2.00
    OVERALL
    2.00
    整體
    1.88
     insgesamt
    1.84
     generally
    1.83
    整体
    1.79
    Act Density 0.232%

    No Known Activations