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

    Neuronpedia

    INDEX
    Explanations

    produces an outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ме
    0.41
    unky
    0.40
    apabb
    0.39
    असल
    0.39
    銮
    0.38
     Seb
    0.38
    ukam
    0.38
     Starter
    0.38
     Brewery
    0.37
     উন্নত
    0.37
    POSITIVE LOGITS
     statistical
    0.42
     edgecolor
    0.41
     adata
    0.41
     stoichi
    0.40
     respect
    0.39
     haircuts
    0.39
     misma
    0.38
     overlap
    0.38
     orbit
    0.38
     ratios
    0.38
    Act Density 0.007%

    No Known Activations