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

    Neuronpedia

    INDEX
    Explanations

    loan or credit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑬
    0.46
    irken
    0.44
    Más
    0.41
    étera
    0.41
    目
    0.40
    Kako
    0.40
     Ovaj
    0.40
    Alarm
    0.40
    ìn
    0.40
     thats
    0.39
    POSITIVE LOGITS
     membantu
    0.41
     জনপ্রিয়তা
    0.39
     سیل
    0.37
     पतला
    0.36
     সম্ভাব্য
    0.36
     resuelve
    0.35
     bitmap
    0.35
    logic
    0.35
     మార్
    0.35
    邏
    0.35
    Act Density 0.002%

    No Known Activations