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

    Neuronpedia

    INDEX
    Explanations

    defining societal groups and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    clay
    0.51
    ق
    0.48
    initro
    0.48
    phantom
    0.47
     clay
    0.46
    filterable
    0.46
    c
    0.45
    l
    0.44
    volver
    0.44
    니다
    0.44
    POSITIVE LOGITS
     Kardashians
    0.45
    MaxPooling
    0.44
     colonists
    0.43
     contradictory
    0.43
     Bishops
    0.43
     Committed
    0.43
     Städte
    0.42
     Développement
    0.42
     Millennials
    0.40
     disputed
    0.40
    Act Density 0.003%

    No Known Activations