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

    Neuronpedia

    INDEX
    Explanations

    variable assignment or naming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     以及
    1.37
     除了
    1.36
     Thị
    1.32
     图
    1.29
     红
    1.29
     當
    1.27
     你
    1.26
     從
    1.25
     胸
    1.25
     Ø
    1.24
    POSITIVE LOGITS
    PACS
    1.18
    手続き
    1.12
    useful
    1.11
     matematika
    1.08
    ワク
    1.08
    Hayes
    1.06
    andrew
    1.05
    crypt
    1.04
    Madrid
    1.03
    magic
    1.03
    Act Density 0.009%

    No Known Activations