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

    Neuronpedia

    INDEX
    Explanations

    company or insurer descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     our
    0.54
     naszych
    0.51
     Operational
    0.50
    我们的
    0.49
     Examples
    0.48
     våra
    0.47
     vores
    0.46
     unseren
    0.45
     Aug
    0.44
    our
    0.44
    POSITIVE LOGITS
    搆
    0.41
     মধ্য
    0.40
    их
    0.40
    某
    0.40
     entidade
    0.39
    ス
    0.38
    纖
    0.38
    Their
    0.38
    รษฐ
    0.37
     sickly
    0.37
    Act Density 0.012%

    No Known Activations