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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rich
    -0.07
    ；↵
    -0.06
    行动
    -0.06
     суб
    -0.06
    getName
    -0.06
    ा।
    -0.06
    .fixture
    -0.06
    Dal
    -0.06
     trovare
    -0.06
    -threatening
    -0.06
    POSITIVE LOGITS
     друга
    0.07
     fieldValue
    0.06
     Brian
    0.06
     Neg
    0.06
    _ETH
    0.06
    ها
    0.06
    či
    0.06
    ÓN
    0.06
    ,ev
    0.06
    忙
    0.06
    Act Density 0.047%

    No Known Activations