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

    Neuronpedia

    INDEX
    Explanations

    favorable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kker
    -0.07
    문
    -0.07
     sacrifices
    -0.07
    ść
    -0.06
    ilateral
    -0.06
     hands
    -0.06
     chồng
    -0.06
     ně
    -0.06
    COD
    -0.06
     حرف
    -0.06
    POSITIVE LOGITS
    /original
    0.07
    ，所以
    0.07
    ”)
    0.07
    .secondary
    0.06
    ::::/
    0.06
    év
    0.06
    ерим
    0.06
    рави
    0.06
     Paladin
    0.06
     CultureInfo
    0.06
    Act Density 0.001%

    No Known Activations