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

    Neuronpedia

    INDEX
    Explanations

    references to blog posts and websites with useful resources

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

    blog posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.35
    rungsseite
    -0.30
    ectady
    -0.29
    IntoConstraints
    -0.28
    </thead>
    -0.27
     stanza
    -0.26
     einzu
    -0.26
     испол
    -0.25
     track
    -0.23
     оказа
    -0.23
    POSITIVE LOGITS
     blog
    0.69
    +#+
    0.67
    évaluateur
    0.66
    InitVars
    0.64
     BLOG
    0.63
    blog
    0.63
     blogging
    0.62
    +#+#
    0.61
    Blog
    0.60
     blogs
    0.60
    Act Density 0.041%

    No Known Activations