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

    Neuronpedia

    INDEX
    Explanations

    Titles and honorifics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itself
    0.73
     자체
    0.56
     or
    0.55
     which
    0.55
     или
    0.52
     strictly
    0.51
     которое
    0.51
     atau
    0.48
     funcionar
    0.48
     jargon
    0.48
    POSITIVE LOGITS
     Jr
    1.01
     Esq
    0.94
    博士
    0.88
     Sr
    0.86
     jr
    0.81
    PhD
    0.80
     OBE
    0.79
     PhD
    0.78
     ಅವರು
    0.74
    who
    0.71
    Act Density 0.066%

    No Known Activations