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

    Neuronpedia

    INDEX
    Explanations

    redirects and cookies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dab
    0.47
     Academic
    0.46
     Rectangle
    0.46
     Progn
    0.44
     Gli
    0.44
     Genre
    0.44
     DAB
    0.44
     enthusiasm
    0.43
     Avenue
    0.42
     exhaustion
    0.42
    POSITIVE LOGITS
    redirect
    0.60
     redirect
    0.54
    Redirect
    0.53
     redirects
    0.52
    baseURL
    0.48
    redirectTo
    0.46
    ﾝ
    0.46
     redir
    0.46
    REDIRECT
    0.45
    cookies
    0.44
    Act Density 0.124%

    No Known Activations