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

    Neuronpedia

    INDEX
    Explanations

    with that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Particular
    0.41
    Particular
    0.39
    曷
    0.38
    其中
    0.37
    并
    0.37
     बि
    0.37
     particular
    0.36
     particulier
    0.36
    Durante
    0.36
    Responder
    0.36
    POSITIVE LOGITS
     banyaknya
    0.61
     adanya
    0.60
    这么多
    0.57
     hindsight
    0.54
    這麼
    0.52
     help
    0.51
     tantas
    0.50
    这么
    0.49
    drawing
    0.48
     hjälp
    0.46
    Act Density 0.007%

    No Known Activations