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

    Neuronpedia

    INDEX
    Explanations

    Sports standings and points

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    吏
    -0.08
    etics
    -0.08
    emo
    -0.08
    ạp
    -0.07
    𝑄
    -0.07
    电动车
    -0.07
    乐团
    -0.07
    .mac
    -0.07
     corrosion
    -0.07
    .onError
    -0.07
    POSITIVE LOGITS
     \|
    0.07
     권
    0.07
    𝚔
    0.07
    蕉
    0.07
     prominently
    0.07
     COP
    0.07
    ┙
    0.07
     פרופ
    0.06
     FIELD
    0.06
    =format
    0.06
    Act Density 0.008%

    No Known Activations