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

    Neuronpedia

    INDEX
    Explanations

    references to blog posts and their structure

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

    blogs and blog posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DebuggerStep
    -0.48
    yntaxException
    -0.45
     Hardware
    -0.41
    endmodule
    -0.40
    CloseOperation
    -0.39
    InteropServices
    -0.39
    rament
    -0.38
     instrumental
    -0.37
    NamedQuery
    -0.36
    Hardware
    -0.36
    POSITIVE LOGITS
     blogs
    1.11
     blog
    1.05
     bloggers
    0.99
     BLOG
    0.99
    Blogs
    0.98
     Blogs
    0.96
     blogging
    0.94
     Blog
    0.94
    Blog
    0.91
    blog
    0.91
    Act Density 0.031%

    No Known Activations