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

    Neuronpedia

    INDEX
    Explanations

    location prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     performance
    -0.06
    Winter
    -0.06
    Minor
    -0.06
    ีล
    -0.06
     HIV
    -0.06
     pprint
    -0.06
    ENCH
    -0.06
    ignon
    -0.06
    ̧
    -0.06
    -stars
    -0.06
    POSITIVE LOGITS
     NotImplementedException
    0.07
    221
    0.06
    -ui
    0.06
     kö
    0.06
     única
    0.06
     myš
    0.06
     cuz
    0.06
    (repository
    0.06
    тою
    0.06
     отказ
    0.06
    Act Density 0.099%

    No Known Activations