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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial loss and associated costs

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

    Currency symbols followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and currency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     million
    -0.75
     millions
    -0.75
     millón
    -0.66
     millones
    -0.64
     млн
    -0.59
     milhões
    -0.59
     Millions
    -0.59
    Millions
    -0.56
     miljoen
    -0.56
     juta
    -0.56
    POSITIVE LOGITS
     hundred
    1.03
    hundred
    0.94
     hundreds
    0.86
     thousand
    0.85
    hundreds
    0.84
     Hundred
    0.82
     Hundreds
    0.80
    Hundred
    0.77
    Hundreds
    0.76
     HUND
    0.75
    Act Density 0.438%

    No Known Activations