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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вок
    -0.07
    紹介
    -0.07
    啊啊
    -0.07
    mh
    -0.07
     Sanity
    -0.06
    　　　　
    -0.06
     Mathematic
    -0.06
     ADD
    -0.06
     layoffs
    -0.06
    ेख
    -0.06
    POSITIVE LOGITS
    :create
    0.06
    cation
    0.06
    holes
    0.06
    �다
    0.06
    âl
    0.06
    |=↵
    0.06
    ги
    0.06
    .asset
    0.06
    .All
    0.06
    ,"%
    0.06
    Act Density 0.000%

    No Known Activations