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

    Neuronpedia

    INDEX
    Explanations

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тено
    0.41
    ExpressCheckout
    0.41
    szön
    0.40
    ্া
    0.39
    تباط
    0.38
    <0xB3>
    0.37
    เจ
    0.36
    गिल
    0.36
     المقدم
    0.35
    enapi
    0.35
    POSITIVE LOGITS
     Determination
    0.38
     २५
    0.36
     Structure
    0.35
     Evaluation
    0.35
     Text
    0.34
     Nod
    0.34
     Feld
    0.33
     realizadas
    0.33
     Loader
    0.32
     Trainers
    0.32
    Act Density 0.002%

    No Known Activations