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

    Neuronpedia

    INDEX
    Explanations

    fuzzy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     condemning
    -0.08
    樯
    -0.08
     Turkey
    -0.07
     Caval
    -0.07
    unordered
    -0.07
    こういう
    -0.07
    酸
    -0.07
    מועצה
    -0.07
    กา
    -0.07
     plur
    -0.07
    POSITIVE LOGITS
    傾
    0.07
     estimate
    0.06
    ?"↵↵
    0.06
    摘要
    0.06
    webElementX
    0.06
    usters
    0.06
    uesto
    0.06
     conclusion
    0.06
     תלוי
    0.06
     subsets
    0.06
    Act Density 0.007%

    No Known Activations