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

    Neuronpedia

    INDEX
    Explanations

    healthcare provider

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    폴
    0.71
    myp
    0.70
     mò
    0.67
    otechnology
    0.67
    printStackTrace
    0.66
     billboards
    0.65
    ophages
    0.64
     Dictionary
    0.64
     tabloid
    0.64
     billboard
    0.64
    POSITIVE LOGITS
     او
    0.94
    或
    0.80
     hoặc
    0.79
     affected
    0.79
    或者
    0.77
     or
    0.77
     أو
    0.77
     when
    0.76
     или
    0.76
     mattered
    0.76
    Act Density 0.004%

    No Known Activations