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

    Neuronpedia

    INDEX
    Explanations

    numbers and mystery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zako
    0.43
     queim
    0.40
    elerde
    0.38
     prépar
    0.37
     pas
    0.36
    ousands
    0.36
     versie
    0.36
     fres
    0.35
     versión
    0.35
    पाक
    0.35
    POSITIVE LOGITS
    mystery
    0.41
    Mystery
    0.39
    franch
    0.38
    crypto
    0.38
    unnumbered
    0.38
     mystery
    0.37
    inicial
    0.36
     viện
    0.36
    doFilter
    0.35
    🤫
    0.35
    Act Density 0.000%

    No Known Activations