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

    Neuronpedia

    INDEX
    Explanations

    street names and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parque
    0.70
     Umgebung
    0.66
     Parque
    0.63
    ২৮
    0.63
     Riverside
    0.62
     Metropolitan
    0.62
     Gino
    0.62
     سرکاری
    0.61
     öffentliche
    0.61
     bairro
    0.60
    POSITIVE LOGITS
     oprac
    0.53
     США
    0.52
    Однако
    0.52
    em
    0.51
    器件
    0.51
    Якщо
    0.51
    ieme
    0.50
     слегка
    0.50
     יכול
    0.49
     правильно
    0.49
    Act Density 0.001%

    No Known Activations