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

    Neuronpedia

    INDEX
    Explanations

    states and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सग
    0.42
    dependencies
    0.41
     Вайлдберриз
    0.41
    ော
    0.40
     vengan
    0.39
    ียม
    0.39
    streets
    0.39
    Bars
    0.39
     กราบ
    0.39
    ជ្ជ
    0.39
    POSITIVE LOGITS
    tipped
    0.39
    decl
    0.39
     tipped
    0.39
     tipping
    0.39
     knotted
    0.37
     chewing
    0.35
     claimed
    0.35
     напа
    0.35
     नौ
    0.34
     accused
    0.34
    Act Density 0.001%

    No Known Activations