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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their roles or actions within various contexts

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

    entities followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     discu
    -0.37
     concession
    -0.37
     parli
    -0.36
    discus
    -0.34
    ản
    -0.34
    propri
    -0.34
    лот
    -0.33
    Zitat
    -0.33
    nanoTime
    -0.32
    arelli
    -0.32
    POSITIVE LOGITS
     mijne
    0.58
    ніципалі
    0.53
     OMITBAD
    0.53
     zijne
    0.52
    EndContext
    0.51
     gruesa
    0.51
     ufficiali
    0.51
     leão
    0.50
     psicológica
    0.50
     Biôgrafia
    0.49
    Act Density 0.369%

    No Known Activations