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

    Neuronpedia

    INDEX
    Explanations

    Reporting technical results

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Validation
    -0.07
    iculos
    -0.07
    מעונ
    -0.07
     voi
    -0.06
    𝘭
    -0.06
    olem
    -0.06
    띤
    -0.06
    l
    -0.06
    人力资源
    -0.06
     subsid
    -0.06
    POSITIVE LOGITS
    ‗
    0.07
    不断
    0.07
    _behavior
    0.07
     repetition
    0.07
     Ord
    0.06
     PREFIX
    0.06
     groundwork
    0.06
    (pkg
    0.06
     reverted
    0.06
    .hw
    0.06
    Act Density 0.421%

    No Known Activations