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

    Neuronpedia

    INDEX
    Explanations

    titles or roles associated with leadership or management positions

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

    leaders' names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.68
     ſtate
    -0.66
     ſever
    -0.60
     juſ
    -0.60
     ſta
    -0.59
     Houſe
    -0.59
     pleaſure
    -0.59
     faſt
    -0.59
     raiſ
    -0.59
     Perſ
    -0.58
    POSITIVE LOGITS
    principalTable
    0.47
     Vorsitzende
    0.43
    InitVars
    0.43
    orteur
    0.42
    자인
    0.41
     
    0.40
     Organisator
    0.39
    帖最后由
    0.38
     noiva
    0.38
     ویکی‌پدیای
    0.36
    Act Density 0.075%

    No Known Activations