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

    Neuronpedia

    INDEX
    Explanations

    data tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ljen
    -0.09
     gambler
    -0.08
     creative
    -0.08
     socialist
    -0.07
     telesc
    -0.07
     barber
    -0.07
     craftsmanship
    -0.07
     diversão
    -0.07
     creativity
    -0.07
     div
    -0.07
    POSITIVE LOGITS
    Relationships
    0.09
     Beziehung
    0.09
    .models
    0.09
    _Filter
    0.09
     Relationships
    0.08
    Worksheet
    0.08
     Beziehungen
    0.08
    relationships
    0.08
     תורה
    0.08
     relaties
    0.08
    Act Density 0.003%

    No Known Activations