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

    Neuronpedia

    INDEX
    Explanations

    cookie

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     전
    -0.07
    typename
    -0.06
    Wir
    -0.06
     Wir
    -0.06
     Urg
    -0.06
    (units
    -0.06
    瞻
    -0.06
     tl
    -0.06
    AxisSize
    -0.06
    POSITIVE LOGITS
    (players
    0.07
     downloader
    0.07
    有效性
    0.07
    影响
    0.06
     coloring
    0.06
     Hockey
    0.06
     SharePoint
    0.06
     venues
    0.06
    🆓
    0.06
    祷
    0.06
    Act Density 0.002%

    No Known Activations