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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ASTIC
    0.34
     särsk
    0.33
    ныя
    0.31
    هاء
    0.30
    APs
    0.30
     Gaines
    0.30
    잖아요
    0.29
    ्यूम
    0.29
     addirittura
    0.29
    信息化
    0.28
    POSITIVE LOGITS
    this
    0.53
     코드
    0.52
    代码
    0.51
    This
    0.50
    ```
    0.50
     This
    0.49
     code
    0.48
    这个
    0.48
    这段
    0.47
     Code
    0.47
    Act Density 0.007%

    No Known Activations