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

    Neuronpedia

    INDEX
    Explanations

    new entities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     about
    0.64
     About
    0.52
     عن
    0.49
     Tentang
    0.48
     अबाउट
    0.48
    about
    0.47
    เกี่ยวกับ
    0.47
     tentang
    0.46
     về
    0.46
    About
    0.45
    POSITIVE LOGITS
     individuos
    0.45
     nuevas
    0.41
     futura
    0.41
     entidades
    0.41
     nuova
    0.41
     nueva
    0.40
     todos
    0.40
     nuevos
    0.39
     fenomen
    0.39
     nuovi
    0.39
    Act Density 0.001%

    No Known Activations