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

    Neuronpedia

    INDEX
    Explanations

    letter "y" as vowel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beschäd
    -0.08
    描
    -0.08
     older
    -0.08
    collections
    -0.08
     collections
    -0.08
     engraved
    -0.07
     datant
    -0.07
     old
    -0.07
     studies
    -0.07
    Older
    -0.07
    POSITIVE LOGITS
     nél
    0.09
     disguised
    0.09
    latent
    0.09
     Sometimes
    0.09
    urricular
    0.09
     Occasionally
    0.08
     guise
    0.08
    anfaat
    0.08
     hút
    0.08
     Zestimate
    0.08
    Act Density 0.019%

    No Known Activations