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

    Neuronpedia

    INDEX
    Explanations

    Hollywood Walk of Fame

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tournament
    -0.08
    Tower
    -0.07
    函数
    -0.07
    ourn
    -0.07
     Billboard
    -0.07
    DWORD
    -0.07
    自然保护
    -0.07
    RP
    -0.07
    .Reporting
    -0.07
    蛹
    -0.07
    POSITIVE LOGITS
    ('\
    0.07
    .getDefault
    0.07
    loading
    0.07
    叮
    0.07
    坚定不移
    0.07
    .nextDouble
    0.07
     beim
    0.07
    ('\\
    0.07
    ](↵
    0.07
    ではなく
    0.07
    Act Density 0.007%

    No Known Activations