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

    Neuronpedia

    INDEX
    Explanations

    references to job positions or roles

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

    position or job

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.46
     actionTypes
    -0.45
    出版年
    -0.44
    siella
    -0.42
     везе
    -0.36
    arXiv
    -0.35
    Delivery
    -0.35
     yyq
    -0.34
    mif
    -0.34
    DELIVERY
    -0.34
    POSITIVE LOGITS
     post
    1.12
     Post
    0.99
    post
    0.98
     posts
    0.94
    Post
    0.90
     Posts
    0.81
     POST
    0.79
     пост
    0.79
     poste
    0.77
    posts
    0.76
    Act Density 0.017%

    No Known Activations