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

    Neuronpedia

    INDEX
    Explanations

    emerging technologies and applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etiquette
    0.91
     when
    0.90
     jogging
    0.87
     QuickBooks
    0.85
     your
    0.83
     sarcastic
    0.82
    respond
    0.82
     dislikes
    0.81
     you
    0.81
     defaul
    0.80
    POSITIVE LOGITS
     biomedical
    1.66
     연구
    1.66
     astrophysical
    1.61
     biotechnology
    1.60
     nanotechnology
    1.58
     미래
    1.50
     nanoparticles
    1.50
     robotics
    1.50
     prototyping
    1.49
     biotechn
    1.49
    Act Density 1.354%

    No Known Activations