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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    irate
    -0.07
    ilot
    -0.07
    邿
    -0.07
    鐵
    -0.07
    Har
    -0.07
     Wil
    -0.07
     Bitmap
    -0.07
     idiot
    -0.07
     heating
    -0.07
    Dod
    -0.07
    POSITIVE LOGITS
     lname
    0.07
    _NAMESPACE
    0.07
    нер
    0.07
     sequential
    0.07
     Spaces
    0.07
     chores
    0.07
     answers
    0.07
    maries
    0.07
     vows
    0.06
    时效
    0.06
    Act Density 0.028%

    No Known Activations