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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reak
    -0.07
     Merkez
    -0.06
     tear
    -0.06
    ardır
    -0.06
    ová
    -0.06
    ンプ
    -0.06
    єв
    -0.06
    unner
    -0.06
    _IE
    -0.06
    肌
    -0.06
    POSITIVE LOGITS
     Update
    0.07
     Fam
    0.07
    .Contact
    0.07
     Gluten
    0.06
    (csv
    0.06
     salon
    0.06
     получения
    0.06
     recovering
    0.06
    loan
    0.06
     stylish
    0.06
    Act Density 0.001%

    No Known Activations