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

    Neuronpedia

    INDEX
    Explanations

    possessive and prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     metering
    0.87
    Divine
    0.73
    +'
    0.71
    虞
    0.70
     যোগাযোগের
    0.68
     കല
    0.68
    imètres
    0.67
    徒歩
    0.67
    тились
    0.67
    лог
    0.66
    POSITIVE LOGITS
     Vẽ
    0.67
     Jr
    0.66
    ូរ
    0.61
    ileges
    0.59
    本セット
    0.58
    まん
    0.58
    ツ
    0.58
     agencia
    0.57
    นาะ
    0.57
    手数料
    0.57
    Act Density 0.009%

    No Known Activations