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

    Neuronpedia

    INDEX
    Explanations

    references to family and personal relationships

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

    names and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    退休
    -0.70
     retired
    -0.68
     retirement
    -0.67
     retiring
    -0.66
     pensioners
    -0.65
     emeritus
    -0.65
     ancianos
    -0.64
     Retirement
    -0.64
    retirement
    -0.63
    脚注の使い方
    -0.63
    POSITIVE LOGITS
     Josh
    0.62
     fiancée
    0.61
     fiancé
    0.60
    Josh
    0.59
     josh
    0.59
     ryan
    0.57
     Brandon
    0.56
     jason
    0.54
     Brittany
    0.53
    Brandon
    0.52
    Act Density 0.013%

    No Known Activations