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

    Neuronpedia

    INDEX
    Explanations

    numeric representations, particularly related to counts or measurements

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

    numbers starting years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.66
    Diweddarwch
    -0.57
    GEBURTSDATUM
    -0.56
    QMetaType
    -0.54
     Мексичка
    -0.54
    httphttps
    -0.53
    లాలు
    -0.51
    featureID
    -0.50
    ंदीखरीदारी
    -0.50
    ABUL
    -0.50
    POSITIVE LOGITS
     juſ
    0.48
    ranno
    0.48
    chtest
    0.47
     Milestone
    0.45
     FontWeight
    0.45
     update
    0.45
     myſelf
    0.45
     milestone
    0.44
     ſche
    0.44
     ſtand
    0.43
    Act Density 0.036%

    No Known Activations