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

    Neuronpedia

    INDEX
    Explanations

    events after 2021

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مؤ
    0.48
    0.47
    Lin
    0.47
    nd
    0.46
    ollen
    0.44
     Estrella
    0.42
    uk
    0.42
     Lin
    0.42
     Appliances
    0.42
    ih
    0.41
    POSITIVE LOGITS
    勧め
    0.54
    птовалю
    0.53
    ヌ
    0.52
    付け
    0.50
     titers
    0.50
    aży
    0.49
     deprive
    0.48
    ترین
    0.47
    pengaruhi
    0.47
    哣
    0.47
    Act Density 0.001%

    No Known Activations