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

    Neuronpedia

    INDEX
    Explanations

    titles and positions related to authority or leadership roles

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

    deputy and assistant roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OnInit
    -0.42
     oprot
    -0.42
    цездатний
    -0.41
     trekken
    -0.41
     protoimpl
    -0.41
     uits
    -0.41
    mobileqq
    -0.41
     vermittelt
    -0.41
    forRoot
    -0.40
    CppMethod
    -0.40
    POSITIVE LOGITS
    ISupport
    0.50
     deputy
    0.46
    PUTY
    0.46
     NSCoder
    0.46
     lieutenant
    0.44
     Deputy
    0.43
    енча
    0.43
     createState
    0.43
    Subtitle
    0.42
     Савезне
    0.42
    Act Density 0.015%

    No Known Activations