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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate quantity or proportionality

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

    spent most of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    withIdentifier
    -0.43
     novos
    -0.43
     nuevos
    -0.43
     novas
    -0.41
     nouve
    -0.41
     chanteur
    -0.40
     nuevas
    -0.40
     sentier
    -0.39
     ocorre
    -0.39
     telas
    -0.39
    POSITIVE LOGITS
     spend
    1.06
     spent
    0.94
    Spend
    0.94
    Spending
    0.93
     spends
    0.91
     spending
    0.91
    spend
    0.91
     Spend
    0.90
     Spent
    0.90
    Spent
    0.89
    Act Density 0.010%

    No Known Activations