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

    Neuronpedia

    INDEX
    Explanations

    New York City

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    1.61
    olio
    1.34
     noastră
    1.34
     conoscere
    1.33
    માં
    1.26
    ों
    1.23
    ীল
    1.20
     پرته
    1.20
    框
    1.20
    সজ্জিত
    1.18
    POSITIVE LOGITS
    л
    1.90
    ল
    1.66
    า
    1.63
    ри
    1.55
    ल
    1.52
     locust
    1.44
    ת
    1.44
    бычно
    1.42
    лите
    1.40
     hammer
    1.38
    Act Density 0.002%

    No Known Activations