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

    Neuronpedia

    INDEX
    Explanations

    phrases ending in 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dans
    0.60
    Für
    0.60
    Pour
    0.52
    对于
    0.52
     insure
    0.51
     для
    0.50
    উ
    0.50
    Đ
    0.49
    Voor
    0.49
    ный
    0.48
    POSITIVE LOGITS
     dint
    0.91
     sheer
    0.86
     virtue
    0.75
    zantine
    0.70
     necessity
    0.68
     osmosis
    0.68
    products
    0.67
     adanya
    0.67
    स्परिक
    0.65
     repeated
    0.62
    Act Density 0.540%

    No Known Activations