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

    Neuronpedia

    INDEX
    Explanations

    credit card charge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meas
    0.46
    usp
    0.42
    يران
    0.42
    计量
    0.39
     Trojan
    0.39
     protagon
    0.39
     reorgan
    0.38
    ه‌ها
    0.38
    asi
    0.38
     Meas
    0.38
    POSITIVE LOGITS
     obese
    0.51
    hashTree
    0.50
    nın
    0.47
    {})
    0.46
    spiele
    0.46
    ্ক
    0.45
     छवियों
    0.44
     사용할
    0.43
     treści
    0.43
     azot
    0.43
    Act Density 0.006%

    No Known Activations