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

    Neuronpedia

    INDEX
    Explanations

    achievements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    俏
    -0.06
    衔接
    -0.06
     DES
    -0.06
     dominant
    -0.06
     mate
    -0.06
    传说
    -0.06
    但也
    -0.06
     Сам
    -0.06
     lay
    -0.06
    ño
    -0.06
    POSITIVE LOGITS
     ingestion
    0.07
    ⛇
    0.07
     vår
    0.06
    .Permission
    0.06
    .Usage
    0.06
    reeting
    0.06
    無い
    0.06
    .posts
    0.06
    "+↵
    0.06
     constitution
    0.06
    Act Density 0.138%

    No Known Activations