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

    Neuronpedia

    INDEX
    Explanations

    ann

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    爽
    -0.07
    tent
    -0.07
    ℹ
    -0.07
     RD
    -0.07
    Serviço
    -0.07
    ;x
    -0.07
    ⨯
    -0.07
    ढ
    -0.06
    驶
    -0.06
    MatrixMode
    -0.06
    POSITIVE LOGITS
     conditioned
    0.07
     שאנ
    0.07
    коль
    0.07
    全明星
    0.07
     Small
    0.07
     highlighting
    0.07
    Lock
    0.07
     courthouse
    0.07
    UL
    0.07
    我们认为
    0.07
    Act Density 0.001%

    No Known Activations