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

    Neuronpedia

    INDEX
    Explanations

    safely and efficiently

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     *****
    -0.07
     Ronaldo
    -0.07
    꼽
    -0.07
    .Al
    -0.07
    +r
    -0.07
    räg
    -0.07
     verk
    -0.07
    ｉ
    -0.07
    𝑟
    -0.07
    id
    -0.06
    POSITIVE LOGITS
    pletely
    0.08
    将于
    0.08
     Ease
    0.08
     battleground
    0.08
    我喜欢
    0.07
    感受
    0.07
     Realm
    0.07
    持仓
    0.07
    亮点
    0.07
    מח
    0.07
    Act Density 0.028%

    No Known Activations