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

    Neuronpedia

    INDEX
    Explanations

    academic papers and research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     technology
    0.67
     emissions
    0.67
    </
    0.65
     join
    0.65
     gone
    0.64
     undergo
    0.64
     during
    0.64
     Oceania
    0.64
     undergoes
    0.64
     retardation
    0.64
    POSITIVE LOGITS
     wikipedia
    0.92
     Wikipedia
    0.91
     ஜெய
    0.90
    Beng
    0.88
     புத்தக
    0.85
    Wikipedia
    0.84
    Papers
    0.82
    netflix
    0.82
     papers
    0.81
    wikipedia
    0.81
    Act Density 0.093%

    No Known Activations