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

    Neuronpedia

    INDEX
    Explanations

    Hotel Indigo Seminyak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    荃灣
    0.42
     ট্রাক
    0.42
    תו
    0.40
    GITHUB
    0.40
    കാ
    0.39
     म्यूजिक
    0.39
     시리즈
    0.39
    фик
    0.39
     Eso
    0.39
     ذ
    0.38
    POSITIVE LOGITS
     lcm
    0.45
     poved
    0.41
    ruppen
    0.41
    enment
    0.39
    hun
    0.39
     hun
    0.38
     colours
    0.38
     valued
    0.37
    leger
    0.37
    enian
    0.37
    Act Density 0.001%

    No Known Activations