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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural elements in text

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

    trial food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.59
     betweenstory
    -0.59
     CreateTagHelper
    -0.56
     wireType
    -0.54
    RTLR
    -0.53
    AndEndTag
    -0.53
     pinulongan
    -0.51
    NameInMap
    -0.50
    StoreMessageInfo
    -0.50
     мәкал
    -0.48
    POSITIVE LOGITS
     חיצוניים
    0.47
     nakalista
    0.43
     Salazar
    0.42
    intended
    0.41
    Примі
    0.39
    pin
    0.39
    PageState
    0.38
     preced
    0.37
     correspon
    0.36
     covenant
    0.35
    Act Density 0.001%

    No Known Activations