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

    Neuronpedia

    INDEX
    Explanations

    old newspaper excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     volunteering
    -0.07
     format
    -0.07
    äre
    -0.07
    yna
    -0.07
     is
    -0.07
     fold
    -0.06
     Labels
    -0.06
    델
    -0.06
    Serializer
    -0.06
    典
    -0.06
    POSITIVE LOGITS
     زیرا
    0.07
    ุค
    0.06
     법
    0.06
    (""))↵
    0.06
    _Target
    0.06
     کارگرد
    0.06
    <Vertex
    0.06
     roommate
    0.06
    ъек
    0.06
     topLevel
    0.06
    Act Density 0.037%

    No Known Activations