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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Safari
    -0.07
     elections
    -0.07
    _>
    -0.07
    /API
    -0.07
    TERNAL
    -0.07
     }}>
    -0.07
    身体
    -0.07
    .Comm
    -0.07
    IELDS
    -0.07
    _DR
    -0.06
    POSITIVE LOGITS
     카
    0.06
    []>↵
    0.06
    负责
    0.06
    сии
    0.06
     Won
    0.06
    れている
    0.06
     пой
    0.06
    ọ
    0.06
     candies
    0.06
    �
    0.06
    Act Density 0.004%

    No Known Activations