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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    लं
    0.44
     est
    0.42
    alam
    0.41
     género
    0.40
    боре
    0.40
    lage
    0.37
     estés
    0.37
    стой
    0.37
    lun
    0.36
    ruž
    0.35
    POSITIVE LOGITS
     самого
    0.43
     року
    0.42
     середи
    0.41
     свого
    0.41
     стороны
    0.40
     skepticism
    0.40
     strany
    0.40
    സിയ
    0.39
     ơn
    0.39
    대로
    0.38
    Act Density 0.002%

    No Known Activations