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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal experience and identity

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

    ages and years old sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.48
    WithIOException
    -0.48
     protoimpl
    -0.46
    SerializeField
    -0.44
    ritsar
    -0.43
     externi
    -0.41
    iprot
    -0.41
    Последние
    -0.41
    fortawesome
    -0.40
    awtextra
    -0.40
    POSITIVE LOGITS
     adult
    0.68
    adult
    0.60
     adults
    0.60
     disambiguazione
    0.59
    Adult
    0.59
     age
    0.58
     ADULT
    0.57
     Adult
    0.57
    Adults
    0.57
     adulthood
    0.56
    Act Density 0.051%

    No Known Activations