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

    Neuronpedia

    INDEX
    Explanations

    Azure App Service configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Web
    0.47
     Web
    0.47
    EnableWeb
    0.43
    ctl
    0.42
    WebApp
    0.40
    dob
    0.39
    Content
    0.37
     web
    0.37
    䈤
    0.37
    Controllers
    0.36
    POSITIVE LOGITS
    slateblue
    0.40
    冷蔵
    0.38
     کوشش
    0.38
     Blackburn
    0.38
    Attempt
    0.38
     fiss
    0.38
     eryth
    0.37
    heading
    0.37
     blackout
    0.37
     torpedo
    0.37
    Act Density 0.004%

    No Known Activations