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

    Neuronpedia

    INDEX
    Explanations

    seeds and buds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Desde
    1.16
    ginas
    1.02
    Estamos
    0.98
    Sebelum
    0.96
    Setelah
    0.93
     Nella
    0.88
    ziale
    0.88
     Existem
    0.88
    ohex
    0.87
     Nós
    0.87
    POSITIVE LOGITS
    soever
    1.03
     vane
    0.95
     dino
    0.91
    ün
    0.91
    iy
    0.90
     NPV
    0.87
     Shou
    0.84
     Immer
    0.84
    ’
    0.83
    зирован
    0.83
    Act Density 0.001%

    No Known Activations