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

    Neuronpedia

    INDEX
    Explanations

    different varieties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    This
    0.59
    Сма
    0.53
    امی
    0.51
    Ther
    0.51
    공
    0.50
    Our
    0.49
    유
    0.49
    연
    0.49
    kowe
    0.48
    ミ
    0.48
    POSITIVE LOGITS
     ⿻
    0.54
     和
    0.51
     সাধারণত
    0.51
     automóvil
    0.51
     parmi
    0.49
     bv
    0.49
     normalerweise
    0.49
     generalmente
    0.49
     ă
    0.48
    並且
    0.48
    Act Density 0.000%

    No Known Activations