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

    Neuronpedia

    INDEX
    Explanations

    comparing quantities or differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    0.50
     Plain
    0.47
     Conver
    0.47
     Adobe
    0.46
     ফেলা
    0.46
     Mile
    0.46
     Grace
    0.46
    א
    0.46
     America
    0.45
    ج
    0.45
    POSITIVE LOGITS
    ız
    0.51
     movilidad
    0.50
    ៈ
    0.49
     susc
    0.48
    َيْ
    0.47
    DBMS
    0.45
     پیغمبر
    0.45
    Riemann
    0.45
     sizin
    0.44
    서를
    0.44
    Act Density 0.059%

    No Known Activations