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

    Neuronpedia

    INDEX
    Explanations

    references to individual names and their associated actions or statements

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

    Precedes the word "said" or synonyms

    np_acts-logits-general · gemini-2.0-flash

    pronouns and names before saying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.99
     propOrder
    -0.90
    Хьажоргаш
    -0.66
     utafitiHapana
    -0.65
    LookAnd
    -0.65
    initWithFrame
    -0.65
     MainAxisSize
    -0.64
    bootstrapcdn
    -0.64
     autorytatywna
    -0.63
     Normdatei
    -0.62
    POSITIVE LOGITS
    .
    0.47
     jullie
    0.39
     Ellos
    0.36
    We
    0.35
     said
    0.34
    I
    0.34
    They
    0.34
     says
    0.33
     They
    0.32
    they
    0.30
    Act Density 0.050%

    No Known Activations