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

    Neuronpedia

    INDEX
    Explanations

    references to monetary amounts or financial figures

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

    dollars with large numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oreille
    -0.42
     folk
    -0.39
     acc
    -0.39
     dentes
    -0.37
     hobby
    -0.36
    Elaboración
    -0.33
     reply
    -0.33
     opinion
    -0.33
     mood
    -0.32
     hobbies
    -0.32
    POSITIVE LOGITS
     billions
    0.79
     $\$
    0.77
    /**
    0.71
     milliard
    0.69
     \$
    0.69
     miliardi
    0.68
    GEBURTSDATUM
    0.68
     milliards
    0.68
    Демографія
    0.66
     millón
    0.66
    Act Density 0.019%

    No Known Activations