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

    Neuronpedia

    INDEX
    Explanations

    specific names and entities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    梩
    0.66
     pabc
    0.64
     एग्जाम्स
    0.62
    ⬝
    0.61
    atributo
    0.59
    ϡ
    0.59
    encerramento
    0.58
    gaussian
    0.58
    0.58
    dbcontext
    0.58
    POSITIVE LOGITS
     ‘
    0.54
     J
    0.51
     ​​
    0.51
     "
    0.50
     University
    0.48
     '
    0.48
     {
    0.47
    0.47
     $
    0.46
     Philippines
    0.46
    Act Density 1.041%

    No Known Activations