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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     denen
    -0.07
    ICLES
    -0.07
    楚
    -0.06
     яких
    -0.06
     Ý
    -0.06
    _chars
    -0.06
    王
    -0.06
     cot
    -0.06
     sách
    -0.06
     Mall
    -0.06
    POSITIVE LOGITS
    현
    0.07
    =fopen
    0.07
    AdapterManager
    0.06
    “그
    0.06
    .Pos
    0.06
    .setVisibility
    0.06
    ừa
    0.06
    WithName
    0.06
     السي
    0.06
     instability
    0.06
    Act Density 0.014%

    No Known Activations