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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -sample
    -0.07
    _Return
    -0.06
    /y
    -0.06
     Mechanical
    -0.06
     anyhow
    -0.06
     diamonds
    -0.06
    _square
    -0.06
     specification
    -0.06
     moist
    -0.06
    ์อ
    -0.06
    POSITIVE LOGITS
     Bulldogs
    0.06
    ”).
    0.06
     Düş
    0.06
     "))
    0.06
    .dom
    0.06
    하였다
    0.06
     HttpRequest
    0.06
     Marseille
    0.06
    黃
    0.06
    ë
    0.06
    Act Density 0.008%

    No Known Activations