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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly those related to counts or quantities

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

    small integer counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     âmes
    -0.50
     enfans
    -0.45
    ándola
    -0.44
     infección
    -0.43
     pouvoit
    -0.43
     adopción
    -0.42
    izante
    -0.41
     zároveň
    -0.39
     pochod
    -0.39
     bluzka
    -0.38
    POSITIVE LOGITS
     dozen
    0.60
    dozen
    0.58
    URLException
    0.55
    ंदीखरीदारी
    0.55
    三四
    0.54
    parsedMessage
    0.54
     للاسماء
    0.54
    featureID
    0.53
     dizaine
    0.52
     several
    0.52
    Act Density 0.023%

    No Known Activations