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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns followed by abstract nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    രേ
    0.47
     codigo
    0.46
     chances
    0.46
    the
    0.45
     código
    0.42
     avid
    0.42
     možnost
    0.41
     crucially
    0.39
     tipo
    0.39
     percentage
    0.38
    POSITIVE LOGITS
     існу
    0.50
     существо
    0.47
     existence
    0.46
     وجود
    0.46
     Zusammenarbeit
    0.45
     bestaan
    0.43
     존재
    0.43
     dibangun
    0.42
     existencia
    0.41
     ሁ
    0.41
    Act Density 0.029%

    No Known Activations