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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    自发
    -0.07
     premature
    -0.07
     Lexington
    -0.07
    .util
    -0.07
    すると
    -0.07
     Buchanan
    -0.07
    FINAL
    -0.06
     Archie
    -0.06
     يستطيع
    -0.06
    _WINDOW
    -0.06
    POSITIVE LOGITS
     qualità
    0.07
     MONTH
    0.07
    🧊
    0.07
    FilterWhere
    0.07
     giám
    0.07
    @Column
    0.07
    얕
    0.07
     offerings
    0.07
    ﺅ
    0.07
    магаз
    0.07
    Act Density 0.019%

    No Known Activations