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

    Neuronpedia

    INDEX
    Explanations

    still

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    symbols
    -0.07
    okens
    -0.07
     heightFor
    -0.07
     Products
    -0.06
    song
    -0.06
     apolog
    -0.06
    *g
    -0.06
    Swagger
    -0.06
    举例
    -0.06
    .each
    -0.06
    POSITIVE LOGITS
     Brasil
    0.07
     urban
    0.07
     reserve
    0.07
    🔫
    0.07
    是不是
    0.06
    冕
    0.06
    當然
    0.06
    ビー
    0.06
    inan
    0.06
     Lowell
    0.06
    Act Density 0.026%

    No Known Activations