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

    Neuronpedia

    INDEX
    Explanations

    repeated occurrences of the letter "A" in various contexts

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

    Followed by colon, uppercase letter, or a multilingual word

    np_acts-logits-general · gemini-2.0-flash

    A followed by a descriptive word or colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalTable
    -0.78
     useAppContext
    -0.72
     Vikipedi
    -0.72
     mouseClicked
    -0.65
     ***!
    -0.65
    multirow
    -0.64
    ScopeManager
    -0.64
    ardis
    -0.63
     دیکھیے
    -0.63
    省市镇
    -0.62
    POSITIVE LOGITS
     A
    1.05
    A
    0.76
    А
    0.74
    getA
    0.66
     А
    0.65
    aA
    0.64
    iA
    0.63
     brancas
    0.61
     B
    0.61
     U
    0.60
    Act Density 0.189%

    No Known Activations