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

    Neuronpedia

    INDEX
    Explanations

    reliable, versatile, polarizing, corporate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     legitimately
    0.48
     legitimate
    0.48
     conspiracies
    0.43
     seriously
    0.43
     unilaterally
    0.42
     savages
    0.42
    ijs
    0.42
     unscrupulous
    0.41
     planet
    0.41
     commitments
    0.41
    POSITIVE LOGITS
     तक
    0.52
     excepciones
    0.50
     Especial
    0.48
    Boulder
    0.47
    伦
    0.46
     علت
    0.46
    قى
    0.46
     evidencia
    0.46
     Investigación
    0.44
     flexibilidad
    0.44
    Act Density 0.003%

    No Known Activations