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

    Neuronpedia

    INDEX
    Explanations

    International Version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Charlottesville
    0.52
     SVM
    0.50
     সিনেম
    0.47
     Houghton
    0.46
     Merton
    0.46
     bookshelf
    0.45
    লা
    0.44
     Clemson
    0.44
     Campan
    0.43
     Atlanta
    0.43
    POSITIVE LOGITS
    既に
    0.49
    ۳
    0.44
    Рис
    0.41
    vive
    0.41
    their
    0.41
    nsic
    0.40
    currency
    0.40
    Луч
    0.39
    gor
    0.39
    microsoft
    0.39
    Act Density 0.000%

    No Known Activations