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

    Neuronpedia

    INDEX
    Explanations

    official

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    マー
    -0.07
     proximity
    -0.07
     lure
    -0.07
     prune
    -0.07
    ifter
    -0.07
     Mare
    -0.07
     lump
    -0.07
    Bor
    -0.07
     ಹೋಗ
    -0.07
     Saras
    -0.07
    POSITIVE LOGITS
     offiziell
    0.15
     الرسمي
    0.15
     Official
    0.15
     offiziellen
    0.14
    Official
    0.14
     ufficial
    0.14
     oficialmente
    0.14
     officielle
    0.14
     officiel
    0.14
     رسمي
    0.13
    Act Density 0.010%

    No Known Activations