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

    Neuronpedia

    INDEX
    Explanations

    adjectives and adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     który
    0.91
     contrairement
    0.89
     nombreuses
    0.89
    ありますが
    0.89
     enige
    0.87
    ueel
    0.87
     поскольку
    0.87
    至于
    0.83
     ktorá
    0.82
     CEA
    0.82
    POSITIVE LOGITS
    ей
    0.97
     Caught
    0.94
    छु
    0.84
    लाल
    0.80
    Bài
    0.79
    rn
    0.74
     Shaped
    0.74
     Hukum
    0.73
     Oxidation
    0.73
    я
    0.72
    Act Density 0.324%

    No Known Activations