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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tir
    -0.07
    нів
    -0.07
     barbecue
    -0.07
     Devils
    -0.06
    μάτων
    -0.06
     Has
    -0.06
     워
    -0.06
     using
    -0.06
     cloudy
    -0.06
    shown
    -0.06
    POSITIVE LOGITS
    ReactDOM
    0.07
    ۲۰
    0.07
    cancellationToken
    0.06
     thanh
    0.06
    ΄
    0.06
    _notice
    0.06
     olmuş
    0.06
    :request
    0.06
     sexdate
    0.06
    -campus
    0.06
    Act Density 0.101%

    No Known Activations