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

    Neuronpedia

    INDEX
    Explanations

    most

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     barbecue
    -0.06
    ashboard
    -0.06
     пит
    -0.06
     Newtown
    -0.06
    [c
    -0.06
     triples
    -0.06
    ूब
    -0.06
    .lucene
    -0.06
     plaque
    -0.06
    Rec
    -0.06
    POSITIVE LOGITS
    mazon
    0.07
     lộ
    0.07
     phổ
    0.07
    ?#
    0.07
     подав
    0.07
     conjunction
    0.07
     backgroundColor
    0.07
     laughter
    0.07
     espan
    0.06
     освіти
    0.06
    Act Density 0.015%

    No Known Activations