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

    Neuronpedia

    INDEX
    Explanations

    names or references to individuals and their relationships in a historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    von or vom followed by name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     creș
    -0.42
    Hentet
    -0.40
     duele
    -0.40
    SortOrder
    -0.40
    IMENT
    -0.40
     Zier
    -0.40
    łaszcza
    -0.39
    augmentation
    -0.38
     zvý
    -0.38
     malheure
    -0.38
    POSITIVE LOGITS
     vom
    1.11
    Vom
    0.84
     Vom
    0.83
    vom
    0.75
     davon
    0.68
     von
    0.64
    Von
    0.64
    ovon
    0.62
     Von
    0.62
    fromnode
    0.62
    Act Density 0.001%

    No Known Activations