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

    Neuronpedia

    INDEX
    Explanations

    the words "rate" or "rates" when they appear in scientific writing

    oai_token-act-pair · gemini-2.0-flash

    rate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rate
    -3.14
     Rate
    -2.98
     rates
    -2.81
    Rate
    -2.80
    rate
    -2.69
     RATE
    -2.66
     Rates
    -2.63
    Rates
    -2.45
    RATE
    -2.36
     RATES
    -2.30
    POSITIVE LOGITS
     MainAxisSize
    0.54
    DockStyle
    0.52
    StoreMessageInfo
    0.51
     NSS
    0.51
    saraba
    0.51
    dafx
    0.51
     Bez
    0.51
    setopt
    0.50
     UITableViewCell
    0.50
    ressum
    0.50
    Act Density 0.305%

    No Known Activations