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

    Neuronpedia

    INDEX
    Explanations

    adjectives following nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ﺍ
    0.59
     ре
    0.54
    iva
    0.54
     ﺍﻟ
    0.52
     Հ
    0.51
    ica
    0.50
    aning
    0.49
     குறிப்பிட்ட
    0.49
    amous
    0.49
    ohner
    0.49
    POSITIVE LOGITS
    رفه
    0.45
    λευ
    0.44
    stopPropagation
    0.42
    齣
    0.41
    源
    0.40
    榜
    0.39
     mů
    0.38
    搆
    0.38
    上下
    0.38
    탈
    0.38
    Act Density 0.006%

    No Known Activations