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

    Neuronpedia

    INDEX
    Explanations

    rates, percentages, and money

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ECUT
    0.39
    alke
    0.38
    羥
    0.38
     всему
    0.37
    ด้
    0.37
     მხ
    0.37
    Dress
    0.36
    ρι
    0.36
    けます
    0.36
     Rohit
    0.36
    POSITIVE LOGITS
     a
    0.64
     investimento
    0.54
     an
    0.49
     beserta
    0.44
     condiciones
    0.43
     investments
    0.42
     inputted
    0.42
     depositing
    0.42
     $
    0.41
     usc
    0.40
    Act Density 0.002%

    No Known Activations