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

    Neuronpedia

    INDEX
    Explanations

    a specific numerical value or measurement in data

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

    large numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chapéu
    -0.55
     iscri
    -0.51
     estabilidad
    -0.49
     destacados
    -0.48
    aspetto
    -0.47
     alturas
    -0.47
    appcompat
    -0.47
     attivo
    -0.47
     praia
    -0.46
     Desenvolvimento
    -0.46
    POSITIVE LOGITS
     thousand
    0.64
     million
    0.63
     XNUMX
    0.60
    Million
    0.60
    0
    0.60
    Thousand
    0.59
     Million
    0.57
     Thousand
    0.57
    一千
    0.57
    ValueGenerated
    0.53
    Act Density 0.023%

    No Known Activations