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

    Neuronpedia

    INDEX
    Explanations

    spot number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    *-
    0.48
     *-
    0.40
    ]-
    0.38
    lite
    0.38
    }$-
    0.38
    HeaderAccept
    0.38
    ージェ
    0.37
    MCP
    0.36
    0.36
    ينه
    0.36
    POSITIVE LOGITS
    ChatMessage
    0.42
    枪
    0.40
    өлү
    0.39
     नॉट
    0.39
    ∶
    0.39
    则
    0.38
    TagName
    0.38
    ొప్పి
    0.38
    Logical
    0.37
    药
    0.37
    Act Density 0.000%

    No Known Activations