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

    Neuronpedia

    INDEX
    Explanations

    rhyming poem generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    বে
    0.80
    عت
    0.73
     esercizi
    0.71
     chemins
    0.68
    لح
    0.67
     absorbed
    0.66
    ी
    0.66
     newly
    0.66
     déplacements
    0.66
     population
    0.66
    POSITIVE LOGITS
     PUBG
    0.82
    ᆭ
    0.80
     Nadal
    0.79
     Buffett
    0.77
     выигра
    0.77
     думать
    0.75
     Coxeter
    0.74
    ifInterface
    0.73
    Pol
    0.73
    squiggle
    0.72
    Act Density 0.001%

    No Known Activations