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

    Neuronpedia

    INDEX
    Explanations

    variables and caring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    эри
    1.14
    аны
    1.12
     Nas
    1.11
    ations
    1.09
    釷
    1.09
    ator
    1.07
    ү
    1.04
    ators
    1.04
    uerung
    1.03
     जवा
    1.03
    POSITIVE LOGITS
    𝐎
    1.46
    设置
    1.35
    straße
    1.25
    BEN
    1.24
    ️⃣
    1.24
     говорить
    1.24
    材质
    1.23
     enormes
    1.23
    ুদ্ধ
    1.21
    𝙩
    1.20
    Act Density 0.000%

    No Known Activations