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

    Neuronpedia

    INDEX
    Explanations

    references to literary works, particularly those related to vampires

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

    Precedes a Name or Title

    np_acts-logits-general · gemini-2.0-flash

    Mr, Mrs, Dr titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.71
     autorytatywna
    -0.54
    đu
    -0.51
    TestingModule
    -0.50
     تانيه
    -0.49
    cahontas
    -0.49
     estekak
    -0.48
     Kof
    -0.48
     rhestr
    -0.48
     ngan
    -0.48
    POSITIVE LOGITS
     Moriarty
    0.61
     Mr
    0.60
     Mrs
    0.60
     Dr
    0.56
    Mrs
    0.55
    poved
    0.53
     treno
    0.52
    bewerken
    0.52
    Mr
    0.51
     Holmes
    0.51
    Act Density 0.185%

    No Known Activations