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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ceramics
    -0.08
     statistic
    -0.07
     환경
    -0.07
    なんて
    -0.06
     epsilon
    -0.06
    俗
    -0.06
    .By
    -0.06
     Appendix
    -0.06
    カル
    -0.06
     Что
    -0.06
    POSITIVE LOGITS
     先
    0.06
     推
    0.06
    ılan
    0.06
     والت
    0.06
    "..
    0.06
     reign
    0.06
     
    0.06
     pocket
    0.06
     Uber
    0.06
     工
    0.06
    Act Density 0.044%

    No Known Activations