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

    Neuronpedia

    INDEX
    Explanations

    references to calculators or calculator-related terms

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

    calculator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.45
     “
    -0.45
     end
    -0.43
    <i>
    -0.42
    –
    -0.40
    <b>
    -0.40
     is
    -0.40
    .
    -0.40
     pre
    -0.40
     
    -0.40
    POSITIVE LOGITS
     Calculator
    2.33
     calculator
    2.25
    Calculator
    2.16
    calculator
    2.03
     calculators
    1.95
     Calcul
    1.25
     CALCUL
    1.23
    culadora
    1.13
    CALCUL
    1.12
    Calcul
    1.07
    Act Density 0.003%

    No Known Activations