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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rh
    -0.08
     distributes
    -0.08
     distribute
    -0.08
     erheb
    -0.08
     esperado
    -0.07
     überrasch
    -0.07
     Zn
    -0.07
     erfre
    -0.07
    罗
    -0.07
    рев
    -0.07
    POSITIVE LOGITS
     चाहता
    0.13
     someday
    0.13
     liebsten
    0.12
     चाहते
    0.11
     graag
    0.11
     quisiera
    0.10
     চান
    0.10
     چاہتے
    0.10
     જાણવા
    0.09
     möglichst
    0.09
    Act Density 0.336%

    No Known Activations