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

    Neuronpedia

    INDEX
    Explanations

    where/wherein/où/где

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ี
    0.59
    डी
    0.49
    existe
    0.49
    ამის
    0.48
    Jangan
    0.47
    ડિયા
    0.47
    आई
    0.46
    डा
    0.46
    ີ
    0.46
    蟶
    0.46
    POSITIVE LOGITS
     wherein
    0.59
     where
    0.55
     où
    0.55
     όπου
    0.53
     где
    0.52
     gdzie
    0.50
     opposites
    0.48
     whereby
    0.48
     waarbij
    0.47
     caractér
    0.45
    Act Density 0.002%

    No Known Activations