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

    Neuronpedia

    INDEX
    Explanations

    article

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Relax
    -0.07
    oš
    -0.06
    /cli
    -0.06
     Bron
    -0.06
    Included
    -0.06
     Ün
    -0.06
    iswa
    -0.06
     HMAC
    -0.06
    startsWith
    -0.06
    _contacts
    -0.06
    POSITIVE LOGITS
     domestically
    0.07
     程
    0.06
     �
    0.06
    atura
    0.06
     rag
    0.06
    чна
    0.06
     trú
    0.06
     deliber
    0.06
     cough
    0.06
    .setState
    0.06
    Act Density 0.005%

    No Known Activations