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

    Neuronpedia

    INDEX
    Explanations

    generate random quotes (programming)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pedido
    -0.08
    gehen
    -0.08
     developments
    -0.08
     madi
    -0.08
     Zel
    -0.08
     cât
    -0.08
     fren
    -0.08
    agnar
    -0.07
     magni
    -0.07
     نسل
    -0.07
    POSITIVE LOGITS
     список
    0.12
     predefined
    0.11
    名单
    0.11
    数组
    0.11
     리스트
    0.11
     массив
    0.10
     constants
    0.10
     curated
    0.10
    列表
    0.10
     배열
    0.10
    Act Density 0.026%

    No Known Activations