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

    Neuronpedia

    INDEX
    Explanations

    terms related to sequential or directional concepts

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

    next episode, down, afternoon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.66
    RefNanny
    -0.62
    CppMethod
    -0.62
    IUrlHelper
    -0.62
     companyId
    -0.59
    parsedMessage
    -0.59
    tagHelper
    -0.57
    OrNil
    -0.55
     alignItems
    -0.55
    URLException
    -0.55
    POSITIVE LOGITS
    下
    2.00
     下
    1.61
    下的
    1.32
    的下
    1.11
    の下
    0.99
    下了
    0.99
    下の
    0.98
     down
    0.92
     under
    0.91
    下が
    0.91
    Act Density 0.001%

    No Known Activations