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

    Neuronpedia

    INDEX
    Explanations

    Design patterns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ורי
    -0.08
    ורים
    -0.08
     people
    -0.07
    대표
    -0.07
     représ
    -0.07
     공부
    -0.07
     nóg
    -0.07
    团
    -0.07
     slices
    -0.07
     prod
    -0.07
    POSITIVE LOGITS
     allgemeinen
    0.10
     పరిస్థిత
    0.09
     levens
    0.09
     allgeme
    0.08
     পরিস্থিত
    0.08
     الحل
    0.08
     çev
    0.08
     उपाय
    0.08
    -solving
    0.08
     xaal
    0.08
    Act Density 0.002%

    No Known Activations