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

    Neuronpedia

    INDEX
    Explanations

    `try`/`except` blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    2.39
    气
    2.19
    ل
    2.16
    方法
    2.11
    anio
    2.10
    数据
    2.10
    お金
    2.06
    新型
    2.03
    滘
    2.01
     несмотря
    2.01
    POSITIVE LOGITS
    glich
    2.39
    𝙨
    2.28
    𝙖
    2.26
    े
    2.24
    𝙣
    2.18
    𝙤
    2.16
    𝙜
    2.14
    𝙡
    2.13
    𝙩
    2.02
    𝙠
    1.98
    Act Density 0.003%

    No Known Activations