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

    Neuronpedia

    INDEX
    Explanations

    There are marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дку
    0.47
    μος
    0.41
    aprendizaje
    0.40
     puterea
    0.39
    人工智能
    0.39
    瑭
    0.39
     daí
    0.38
    倞
    0.38
     σας
    0.37
     ahí
    0.37
    POSITIVE LOGITS
     gotovo
    0.44
     Network
    0.41
     Crown
    0.36
     centrally
    0.36
     Nid
    0.36
     Lapp
    0.36
     more
    0.36
     Tian
    0.36
     అత్య
    0.36
     Status
    0.36
    Act Density 0.000%

    No Known Activations