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

    Neuronpedia

    INDEX
    Explanations

    Troy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    carrier
    -0.06
    TestFixture
    -0.06
     openness
    -0.06
    柄
    -0.06
    ],[
    -0.06
     identifiers
    -0.06
    conde
    -0.06
     Rabbit
    -0.06
    elle
    -0.06
    ersions
    -0.06
    POSITIVE LOGITS
     Troy
    0.08
    asjon
    0.07
     sınır
    0.07
     akşam
    0.07
     commem
    0.06
    -tab
    0.06
    .bad
    0.06
     pari
    0.06
    641
    0.06
    pron
    0.06
    Act Density 0.001%

    No Known Activations