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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols that represent dialogue or quotations

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

    Roman empire/history context

    np_acts-logits-general · gemini-2.0-flash

    Roman calendar, festivals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.72
     الحره
    -0.63
    Skocz
    -0.59
    pidou
    -0.55
    BeginInit
    -0.54
    ⓘ
    -0.53
     المعيارى
    -0.53
    AccessorTable
    -0.51
     ujednoznacz
    -0.51
    出版年
    -0.49
    POSITIVE LOGITS
     Roman
    0.99
    Roman
    0.89
     Rome
    0.82
     ROMAN
    0.81
     Romans
    0.80
     roman
    0.80
     Caesar
    0.79
     romana
    0.77
    Caesar
    0.74
     Caesars
    0.74
    Act Density 0.161%

    No Known Activations