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

    Neuronpedia

    INDEX
    Explanations

    past participles followed by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ad
    0.61
    and
    0.55
    an
    0.54
     बड़ी
    0.52
    anın
    0.51
     αποτέ
    0.50
    า
    0.50
     बड़ी
    0.48
     बड़े
    0.48
    fords
    0.47
    POSITIVE LOGITS
    с
    0.74
    س
    0.64
    :
    0.52
    ;
    0.52
    ت
    0.51
    ление
    0.49
    دا
    0.49
    स
    0.48
    з
    0.47
    ス
    0.47
    Act Density 0.378%

    No Known Activations