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

    Neuronpedia

    INDEX
    Explanations

    East Asian and West regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ITY
    0.78
    intern
    0.73
    ity
    0.72
    Castro
    0.69
    Processed
    0.69
     sin
    0.67
    Corre
    0.65
    業務用
    0.65
     लिहाज
    0.65
    BT
    0.64
    POSITIVE LOGITS
     Coast
    1.55
     coast
    1.43
    ward
    1.39
    coast
    1.38
    ERN
    1.38
    wards
    1.34
    Coast
    1.31
    side
    1.30
     Indies
    1.21
    र्न
    1.20
    Act Density 0.014%

    No Known Activations