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

    Neuronpedia

    INDEX
    Explanations

    connections between influence and decision-making processes

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

    informs, influences, and guides outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.79
    AndEndTag
    -0.73
     AssemblyCulture
    -0.71
    WebVitals
    -0.62
    ChildScrollView
    -0.62
     Paglinawan
    -0.61
     useAppContext
    -0.60
    AutoScaleMode
    -0.58
    出版年
    -0.58
    ElementException
    -0.57
    POSITIVE LOGITS
     influences
    0.36
     significantly
    0.35
     grounded
    0.34
     influencing
    0.31
    Tail
    0.31
    原
    0.30
    tail
    0.28
     influenced
    0.28
    tic
    0.27
    尾
    0.27
    Act Density 0.086%

    No Known Activations