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

    Neuronpedia

    INDEX
    Explanations

    document suffixes (-endum, -arium, -orium)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ism
    0.49
     SOM
    0.47
    scm
    0.43
     ACM
    0.43
     BOM
    0.42
    crm
    0.42
    ISM
    0.41
     Som
    0.41
     চিং
    0.40
    CRM
    0.40
    POSITIVE LOGITS
    arium
    0.72
    urium
    0.64
    atorium
    0.64
    ariums
    0.62
    atum
    0.58
    orium
    0.55
    endum
    0.54
    ATUM
    0.54
     memorandum
    0.53
    quium
    0.52
    Act Density 0.009%

    No Known Activations