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

    Neuronpedia

    INDEX
    Explanations

    customer segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pioneer
    0.46
     ści
    0.45
     مرتبط
    0.43
     compelling
    0.43
     va
    0.42
     dimensional
    0.42
     disciples
    0.42
     very
    0.41
     لہ
    0.41
     پیم
    0.41
    POSITIVE LOGITS
     Erskine
    0.45
    óg
    0.44
    َق
    0.44
    ovania
    0.42
    交换
    0.42
    تقدم
    0.42
    прос
    0.42
    퀘
    0.42
    ларын
    0.41
     Progressives
    0.41
    Act Density 0.000%

    No Known Activations