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

    Neuronpedia

    INDEX
    Explanations

    poles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    800
    -0.07
     alloys
    -0.07
    ifferences
    -0.06
    legend
    -0.06
    rado
    -0.06
    eping
    -0.06
    Brun
    -0.06
     Zuckerberg
    -0.06
     Litecoin
    -0.06
    хи
    -0.06
    POSITIVE LOGITS
    }}{{
    0.06
    थ
    0.06
     simply
    0.06
     dictated
    0.06
     Tay
    0.06
    _ADMIN
    0.06
     ain
    0.06
    BarButtonItem
    0.06
     POST
    0.06
    'field
    0.06
    Act Density 0.009%

    No Known Activations