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

    Neuronpedia

    INDEX
    Explanations

    first option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     २०२२
    0.78
    ⑵
    0.71
    [-
    0.70
     dernier
    0.69
     Ninth
    0.67
     २०२
    0.66
    BBB
    0.66
     వు
    0.66
    ''(
    0.64
    henburg
    0.64
    POSITIVE LOGITS
     A
    1.31
    A
    1.26
     first
    1.20
     pertama
    1.11
     First
    1.06
     primera
    1.03
     primeira
    1.03
     А
    1.02
    first
    1.02
     первом
    0.98
    Act Density 0.626%

    No Known Activations