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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cu
    -0.07
     drinkers
    -0.07
    ardin
    -0.07
     В
    -0.06
    -design
    -0.06
    政府采购
    -0.06
     encryption
    -0.06
     essays
    -0.06
    个百分
    -0.06
     irritated
    -0.06
    POSITIVE LOGITS
    ᵌ
    0.08
    _FINE
    0.07
    🆎
    0.07
    вл
    0.07
    命名
    0.07
    풜
    0.07
    岨
    0.07
    ቲ
    0.07
    גמר
    0.07
    ưởng
    0.07
    Act Density 0.034%

    No Known Activations