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

    Neuronpedia

    INDEX
    Explanations

    makeup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Джон
    -0.07
    یره
    -0.07
    ETwitter
    -0.06
     سلس
    -0.06
    ilar
    -0.06
     episodes
    -0.06
    маг
    -0.06
    _rad
    -0.06
    Ult
    -0.06
     Dim
    -0.06
    POSITIVE LOGITS
    格
    0.07
    .startActivity
    0.07
     textiles
    0.07
     Sioux
    0.06
     toto
    0.06
    σωπ
    0.06
     matchmaking
    0.06
    もっと
    0.06
     findAll
    0.06
    )&&(
    0.06
    Act Density 0.000%

    No Known Activations