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

    Neuronpedia

    INDEX
    Explanations

    networking opens doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ordenar
    0.56
    ைட்
    0.53
     Chayin
    0.53
    ഗ്യ
    0.53
    טת
    0.52
     macar
    0.51
    僄
    0.51
     مارت
    0.50
    峎
    0.50
     sillonné
    0.50
    POSITIVE LOGITS
    0.47
     an
    0.44
    acu
    0.42
     ...
    0.41
    ү
    0.39
     Sun
    0.39
     仮
    0.39
    asting
    0.38
     weigh
    0.38
    それに
    0.38
    Act Density 0.002%

    No Known Activations