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

    Neuronpedia

    INDEX
    Explanations

    bracket "["

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Arch
    -0.08
     Arch
    -0.08
     তাকে
    -0.08
    <Address
    -0.08
    事实
    -0.08
     Ane
    -0.07
     रिकॉर्ड
    -0.07
     ARCH
    -0.07
     Auf
    -0.07
    iori
    -0.07
    POSITIVE LOGITS
    гач
    0.08
     års
    0.08
    終了
    0.08
     Jonas
    0.08
     emojis
    0.07
     customization
    0.07
     date
    0.07
    еша
    0.07
     comprehension
    0.07
     tasse
    0.07
    Act Density 0.007%

    No Known Activations