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

    Neuronpedia

    INDEX
    Explanations

    sc words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lysed
    0.71
     fond
    0.70
     certain
    0.69
     aider
    0.66
     Certain
    0.65
     app
    0.64
     sho
    0.64
     entire
    0.64
    acic
    0.63
     Microsoft
    0.62
    POSITIVE LOGITS
    EDULE
    0.88
    andinavian
    0.87
    affold
    0.87
    ίου
    0.86
    ytale
    0.85
    apes
    0.85
    Sc
    0.85
    scraper
    0.84
     sc
    0.84
    FDMA
    0.83
    Act Density 0.091%

    No Known Activations