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

    Neuronpedia

    INDEX
    Explanations

    code snippets/languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cot
    -0.07
    iosis
    -0.07
    被判
    -0.07
    雷斯
    -0.07
     chop
    -0.07
    ⇵
    -0.07
    듭
    -0.07
    information
    -0.07
     WORLD
    -0.07
    .safe
    -0.07
    POSITIVE LOGITS
     arcade
    0.08
     Lamar
    0.07
     Control
    0.06
     thành
    0.06
     trial
    0.06
    까지
    0.06
     principales
    0.06
     posible
    0.06
    vl
    0.06
    .kotlin
    0.06
    Act Density 0.027%

    No Known Activations