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

    Neuronpedia

    INDEX
    Explanations

    categories and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    赁
    0.44
    ▛
    0.44
     uranyl
    0.44
    𒊑
    0.43
    ೂರ್
    0.42
     వాటి
    0.42
     অনুরূপ
    0.41
    ꒷
    0.41
     जताया
    0.40
    NEUTRON
    0.40
    POSITIVE LOGITS
    k
    0.44
    C
    0.42
      
    0.41
     b
    0.40
     d
    0.39
     –
    0.38
    0.37
     u
    0.37
     می‌کند
    0.37
    b
    0.37
    Act Density 0.053%

    No Known Activations