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

    Neuronpedia

    INDEX
    Explanations

    free,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    したり
    0.48
    утбу
    0.46
     hMut
    0.45
     inadequ
    0.42
     Parlamento
    0.40
    하거나
    0.40
     architectures
    0.40
    ಳೆದ
    0.40
    শ্রেষ্ঠ
    0.40
     imparts
    0.40
    POSITIVE LOGITS
     क्योंकि
    0.53
     কারণ
    0.48
    l
    0.46
     because
    0.46
    とのこと
    0.43
    n
    0.42
     കാരണം
    0.41
     karena
    0.41
    because
    0.41
     कोणत्याही
    0.40
    Act Density 0.009%

    No Known Activations