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

    Neuronpedia

    INDEX
    Explanations

    references to articles or blog posts and words indicating they are well-written or valuable.

    oai_token-act-pair · gemini-2.0-flash

    post

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.68
    DockStyle
    -0.61
    tagHelperRunner
    -0.60
    EndInit
    -0.57
    ValueStyle
    -0.56
    期刊论文
    -0.50
    InjectAttribute
    -0.50
    consulté
    -0.50
     initComponents
    -0.49
    ViewFeatures
    -0.48
    POSITIVE LOGITS
     post
    1.13
    post
    0.82
    Post
    0.72
     pós
    0.71
     Post
    0.63
    thâu
    0.61
     POST
    0.59
     пост
    0.59
    Jereo
    0.59
     незавершена
    0.57
    Act Density 4.174%

    No Known Activations