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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lol
    -0.09
    enderror
    -0.08
     પૈ
    -0.08
     conseil
    -0.08
     seuil
    -0.08
     Beginners
    -0.08
     Verg
    -0.08
     mikt
    -0.07
     rond
    -0.07
     recording
    -0.07
    POSITIVE LOGITS
    交流
    0.08
     ಸಂ
    0.08
     ಗಳ
    0.08
     تعامل
    0.08
     ಸಂಪರ್ಕ
    0.07
    ಾಷ್ಟ
    0.07
     WAN
    0.07
     Wechsel
    0.07
    751
    0.07
     которыми
    0.07
    Act Density 0.004%

    No Known Activations