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

    Neuronpedia

    INDEX
    Explanations

    references to military training and regimental organization

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

    Follows "the" or a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    Queen, Defence, Royal Guard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     >=",
    -0.54
     behavior
    -0.52
    下载附件
    -0.51
    SharedCtor
    -0.50
     sirup
    -0.49
    olybdenum
    -0.49
    是怎么回事
    -0.48
     Erle
    -0.47
     Behavior
    -0.47
    焦
    -0.47
    POSITIVE LOGITS
    OGND
    0.63
    Defence
    0.58
     Territorial
    0.56
     Catering
    0.56
     Royal
    0.56
     Defence
    0.55
    REME
    0.53
     Queen
    0.52
    PYX
    0.51
     ROYAL
    0.50
    Act Density 0.157%

    No Known Activations