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

    Neuronpedia

    INDEX
    Explanations

    references to flags, particularly their significance and usage in various contexts

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

    Logos, emblems, or heraldic symbols

    np_acts-logits-general · gemini-2.0-flash

    symbols and logos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FormTagHelper
    -0.75
    FieldNumber
    -0.64
    ulose
    -0.62
    TabIndex
    -0.61
    WriteTagHelper
    -0.60
     שוליים
    -0.60
     intptr
    -0.59
    :✨
    -0.58
     ब्रेकडाउन
    -0.57
    modb
    -0.57
    POSITIVE LOGITS
     symbol
    1.68
     logo
    1.64
     emblem
    1.59
     symbols
    1.53
     logos
    1.39
     flag
    1.38
     emblems
    1.38
     Symbol
    1.35
    symbol
    1.33
     Logo
    1.32
    Act Density 0.217%

    No Known Activations