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

    Neuronpedia

    INDEX
    Explanations

    planning/zoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    就
    -0.07
    COMMON
    -0.06
    iggers
    -0.06
     sorry
    -0.06
    ’↵
    -0.06
    ोष
    -0.06
     heartfelt
    -0.06
    ें↵
    -0.06
    esk
    -0.06
    船
    -0.06
    POSITIVE LOGITS
    마사지
    0.07
     infos
    0.07
    _Abstract
    0.07
     東京
    0.06
    .setString
    0.06
     FEC
    0.06
     Sergey
    0.06
    	CG
    0.06
    rejected
    0.06
    tableView
    0.06
    Act Density 0.056%

    No Known Activations